Adding speaker identification

.gitmodules

@@ -1,3 +1,6 @@
 [submodule "whisper.cpp"]
 	path = whisper.cpp
 	url = https://github.com/ggerganov/whisper.cpp
+[submodule "whisper_diarization"]
+	path = whisper_diarization
+	url = https://github.com/MahmoudAshraf97/whisper-diarization

buzz/locale/ca_ES/LC_MESSAGES/buzz.po

@@ -7,7 +7,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: buzz\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2025-03-06 19:12+0200\n"
+"POT-Creation-Date: 2025-04-06 20:58+0300\n"
 "PO-Revision-Date: 2023-02-15 05:01+0000\n"
 "Last-Translator: Jordi Mas i Hernàndez <jmas@softcatala.org>\n"
 "Language-Team: Catalan <jmas@softcatala.org>\n"
@@ -73,122 +73,127 @@ msgid "Danish"
 msgstr ""
 
 #: buzz/widgets/preferences_dialog/general_preferences_widget.py:38
+#: buzz/transcriber/transcriber.py:50
+msgid "Dutch"
+msgstr ""
+
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:39
 #: buzz/transcriber/transcriber.py:40
 msgid "German"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:39
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:40
 #: buzz/transcriber/transcriber.py:41
 msgid "Spanish"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:40
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:41
 #: buzz/transcriber/transcriber.py:53
 msgid "Italian"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:41
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:42
 #: buzz/transcriber/transcriber.py:45
 msgid "Japanese"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:42
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:43
 #: buzz/transcriber/transcriber.py:80
 msgid "Latvian"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:43
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:44
 #: buzz/transcriber/transcriber.py:48
 msgid "Polish"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:44
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:45
 #: buzz/transcriber/transcriber.py:59
 msgid "Ukrainian"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:45
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:46
 msgid "Chinese (Simplified)"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:46
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:47
 msgid "Chinese (Traditional)"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:84
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:85
 msgid "Restart required!"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:88
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:89
 #, fuzzy
 msgid "Ui Language"
 msgstr "Idioma:"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:96
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:97
 msgid "Font Size"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:105
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:106
 msgid "Test"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:111
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:112
 msgid "OpenAI API key"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:124
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:125
 msgid "OpenAI base url"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:133
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:134
 msgid "Default export file name"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:139
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:140
 msgid "Enable live recording transcription export"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:145
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:146
 #: buzz/widgets/preferences_dialog/folder_watch_preferences_widget.py:47
 #: buzz/widgets/preferences_dialog/folder_watch_preferences_widget.py:50
 msgid "Browse"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:164
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:165
 msgid "Export folder"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:175
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:176
 #, fuzzy
 msgid "Live recording mode"
 msgstr "Enregistrament en viu"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:200
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:206
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:201
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:207
 msgid "OpenAI API Key Test"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:201
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:202
 msgid ""
 "Your API key is valid. Buzz will use this key to perform Whisper API "
 "transcriptions and AI translations."
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:217
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:218
 msgid "Invalid API key"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:218
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:219
 msgid ""
 "API supports only base64 characters (A-Za-z0-9+/=_-). Other characters in "
 "API key may cause errors."
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:236
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:237
 msgid "Select Export Folder"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:296
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:297
 msgid ""
 "OpenAI API returned invalid response. Please check the API url or your key. "
 "Transcription and translation may still work if the API does not support key "
@@ -527,56 +532,131 @@ msgstr ""
 msgid "Timestamps"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:146
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:150
 msgid "Export"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:160
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:164
 #: buzz/transcriber/transcriber.py:24
 msgid "Translate"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:170
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:168
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:174
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:166
 msgid "Resize"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:269
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:187
+msgid "Identify Speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:286
 msgid "API Key Required"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:270
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:287
 msgid "Please enter OpenAI API Key in preferences"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:150
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:148
 msgid "Resize Options"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:161
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:159
 msgid "Desired subtitle length"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:186
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:184
 msgid "Merge Options"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:197
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:195
 msgid "Merge by gap"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:205
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:203
 msgid "Split by punctuation"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:213
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:211
 msgid "Split by max length"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:225
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:223
 msgid "Merge"
 msgstr ""
 
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:101
+msgid "1/9 Collecting transcripts"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:115
+msgid "2/9 Loading audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:124
+msgid "3/9 Loading alignment model"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:130
+msgid "4/9 Preparing audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:142
+#, fuzzy
+msgid "5/9 Preparing transcripts"
+msgstr "Obre una transcripció"
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:160
+msgid "6/9 Converting audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:174
+msgid "7/9 Identifying speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:184
+msgid "8/9 Mapping speakers to transcripts"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:233
+msgid "9/9 Identification done"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:278
+msgid "Step 1: Identify speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:290
+msgid "Identify"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:300
+msgid "Ready to identify speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:302
+msgid "Audio file not found"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:318
+msgid "Step 2: Name speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:333
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:431
+msgid "Play sample"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:348
+msgid "Merge speaker sentences"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:353
+#, fuzzy
+msgid "Save"
+msgstr "Desa el fitxer"
+
 #: buzz/widgets/transcription_viewer/export_transcription_menu.py:78
 msgid "Save File"
 msgstr "Desa el fitxer"
@@ -684,10 +764,6 @@ msgstr ""
 msgid "Turkish"
 msgstr ""
 
-#: buzz/transcriber/transcriber.py:50
-msgid "Dutch"
-msgstr ""
-
 #: buzz/transcriber/transcriber.py:51
 msgid "Arabic"
 msgstr ""

buzz/locale/da_DK/LC_MESSAGES/buzz.po

@@ -2,7 +2,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: \n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2025-03-06 19:12+0200\n"
+"POT-Creation-Date: 2025-04-06 20:58+0300\n"
 "PO-Revision-Date: \n"
 "Last-Translator: Ole Guldberg2 <xalt7x.service@gmail.com>\n"
 "Language-Team: \n"
@@ -70,103 +70,108 @@ msgid "Danish"
 msgstr ""
 
 #: buzz/widgets/preferences_dialog/general_preferences_widget.py:38
+#: buzz/transcriber/transcriber.py:50
+msgid "Dutch"
+msgstr ""
+
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:39
 #: buzz/transcriber/transcriber.py:40
 msgid "German"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:39
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:40
 #: buzz/transcriber/transcriber.py:41
 msgid "Spanish"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:40
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:41
 #: buzz/transcriber/transcriber.py:53
 msgid "Italian"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:41
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:42
 #: buzz/transcriber/transcriber.py:45
 msgid "Japanese"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:42
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:43
 #: buzz/transcriber/transcriber.py:80
 msgid "Latvian"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:43
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:44
 #: buzz/transcriber/transcriber.py:48
 msgid "Polish"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:44
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:45
 #: buzz/transcriber/transcriber.py:59
 #, fuzzy
 msgid "Ukrainian"
 msgstr "tilbageværende"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:45
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:46
 msgid "Chinese (Simplified)"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:46
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:47
 msgid "Chinese (Traditional)"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:84
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:85
 msgid "Restart required!"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:88
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:89
 #, fuzzy
 msgid "Ui Language"
 msgstr "Sprog:"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:96
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:97
 msgid "Font Size"
 msgstr "Skriftypestørrelse"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:105
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:106
 msgid "Test"
 msgstr "Test"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:111
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:112
 msgid "OpenAI API key"
 msgstr "OpenAI API-nøgle"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:124
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:125
 msgid "OpenAI base url"
 msgstr "OpenAI base-URL"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:133
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:134
 msgid "Default export file name"
 msgstr "Standard eksport filnavn"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:139
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:140
 msgid "Enable live recording transcription export"
 msgstr "Slå transkription af live optagelse eksport til"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:145
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:146
 #: buzz/widgets/preferences_dialog/folder_watch_preferences_widget.py:47
 #: buzz/widgets/preferences_dialog/folder_watch_preferences_widget.py:50
 msgid "Browse"
 msgstr "Gennemse"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:164
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:165
 msgid "Export folder"
 msgstr "Eksportmappe"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:175
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:176
 #, fuzzy
 msgid "Live recording mode"
 msgstr "Live optagelsesmode"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:200
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:206
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:201
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:207
 msgid "OpenAI API Key Test"
 msgstr "OpenAI API Nøgle test"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:201
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:202
 msgid ""
 "Your API key is valid. Buzz will use this key to perform Whisper API "
 "transcriptions and AI translations."
@@ -174,12 +179,12 @@ msgstr ""
 "Din API nøgle er gyldig. Buzz vil benytte nøglen til at anvende Whisper API "
 "transkription og AI oversættelser."
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:217
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:218
 #, fuzzy
 msgid "Invalid API key"
 msgstr "Ugyldig API-nøgle"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:218
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:219
 msgid ""
 "API supports only base64 characters (A-Za-z0-9+/=_-). Other characters in "
 "API key may cause errors."
@@ -187,11 +192,11 @@ msgstr ""
 "API supporterer kun base64 tegn (A-Za-z0-9+/=_-). Andre tegn i API-nøglen "
 "kan guve fejl. "
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:236
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:237
 msgid "Select Export Folder"
 msgstr "Vælg eksport-mappe"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:296
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:297
 msgid ""
 "OpenAI API returned invalid response. Please check the API url or your key. "
 "Transcription and translation may still work if the API does not support key "
@@ -524,56 +529,131 @@ msgstr "Vis"
 msgid "Timestamps"
 msgstr "Tidsstempler"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:146
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:150
 msgid "Export"
 msgstr "Eksporter"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:160
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:164
 #: buzz/transcriber/transcriber.py:24
 msgid "Translate"
 msgstr "Oversæt"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:170
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:168
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:174
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:166
 msgid "Resize"
 msgstr "Behandel størrelse"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:269
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:187
+msgid "Identify Speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:286
 msgid "API Key Required"
 msgstr "API-nøgle påkrævet"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:270
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:287
 msgid "Please enter OpenAI API Key in preferences"
 msgstr "Indtast venligst OpenAI API-nøgle i indstillinger"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:150
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:148
 msgid "Resize Options"
 msgstr "Størrelsesindstillinger"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:161
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:159
 msgid "Desired subtitle length"
 msgstr "Ønskede undertekst længde"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:186
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:184
 msgid "Merge Options"
 msgstr "Sammenfletningsindstillinger"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:197
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:195
 msgid "Merge by gap"
 msgstr "Sammenflet ved hul"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:205
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:203
 msgid "Split by punctuation"
 msgstr "Split ved punktum"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:213
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:211
 msgid "Split by max length"
 msgstr "Split ved max længde"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:225
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:223
 msgid "Merge"
 msgstr "Sammenflet"
 
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:101
+msgid "1/9 Collecting transcripts"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:115
+msgid "2/9 Loading audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:124
+msgid "3/9 Loading alignment model"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:130
+msgid "4/9 Preparing audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:142
+#, fuzzy
+msgid "5/9 Preparing transcripts"
+msgstr "Åben transkription"
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:160
+msgid "6/9 Converting audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:174
+msgid "7/9 Identifying speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:184
+msgid "8/9 Mapping speakers to transcripts"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:233
+msgid "9/9 Identification done"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:278
+msgid "Step 1: Identify speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:290
+msgid "Identify"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:300
+msgid "Ready to identify speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:302
+msgid "Audio file not found"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:318
+msgid "Step 2: Name speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:333
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:431
+msgid "Play sample"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:348
+msgid "Merge speaker sentences"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:353
+#, fuzzy
+msgid "Save"
+msgstr "Gem fil"
+
 #: buzz/widgets/transcription_viewer/export_transcription_menu.py:78
 msgid "Save File"
 msgstr "Gem fil"
@@ -681,10 +761,6 @@ msgstr ""
 msgid "Turkish"
 msgstr ""
 
-#: buzz/transcriber/transcriber.py:50
-msgid "Dutch"
-msgstr ""
-
 #: buzz/transcriber/transcriber.py:51
 msgid "Arabic"
 msgstr ""

buzz/locale/de_DE/LC_MESSAGES/buzz.po

@@ -6,7 +6,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: \n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2025-03-06 19:13+0200\n"
+"POT-Creation-Date: 2025-04-06 20:58+0300\n"
 "PO-Revision-Date: 2025-03-05 14:41+0100\n"
 "Last-Translator: \n"
 "Language-Team: \n"
@@ -72,100 +72,105 @@ msgid "Danish"
 msgstr "Dänisch"
 
 #: buzz/widgets/preferences_dialog/general_preferences_widget.py:38
+#: buzz/transcriber/transcriber.py:50
+msgid "Dutch"
+msgstr "Niederländisch"
+
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:39
 #: buzz/transcriber/transcriber.py:40
 msgid "German"
 msgstr "Deutsch"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:39
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:40
 #: buzz/transcriber/transcriber.py:41
 msgid "Spanish"
 msgstr "Spanisch"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:40
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:41
 #: buzz/transcriber/transcriber.py:53
 msgid "Italian"
 msgstr "Italienisch"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:41
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:42
 #: buzz/transcriber/transcriber.py:45
 msgid "Japanese"
 msgstr "Japanisch"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:42
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:43
 #: buzz/transcriber/transcriber.py:80
 msgid "Latvian"
 msgstr "Lettisch"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:43
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:44
 #: buzz/transcriber/transcriber.py:48
 msgid "Polish"
 msgstr "Polnisch"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:44
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:45
 #: buzz/transcriber/transcriber.py:59
 msgid "Ukrainian"
 msgstr "Ukrainisch"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:45
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:46
 msgid "Chinese (Simplified)"
 msgstr "Chinesisch (vereinfacht)"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:46
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:47
 msgid "Chinese (Traditional)"
 msgstr "Chinesisch (traditionell)"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:84
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:85
 msgid "Restart required!"
 msgstr "Neustart erforderlich!"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:88
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:89
 msgid "Ui Language"
 msgstr "Sprache der Benutzeroberfläche"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:96
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:97
 msgid "Font Size"
 msgstr "Schriftgröße"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:105
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:106
 msgid "Test"
 msgstr "Test"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:111
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:112
 msgid "OpenAI API key"
 msgstr "OpenAI-API-Schlüssel"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:124
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:125
 msgid "OpenAI base url"
 msgstr "OpenAI-Basis-URL"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:133
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:134
 msgid "Default export file name"
 msgstr "Standardname der Exportdatei"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:139
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:140
 msgid "Enable live recording transcription export"
 msgstr "Export von Live-Aufnahmetranskriptionen aktivieren"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:145
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:146
 #: buzz/widgets/preferences_dialog/folder_watch_preferences_widget.py:47
 #: buzz/widgets/preferences_dialog/folder_watch_preferences_widget.py:50
 msgid "Browse"
 msgstr "Durchsuchen"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:164
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:165
 msgid "Export folder"
 msgstr "Exportordner"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:175
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:176
 msgid "Live recording mode"
 msgstr "Live-Aufnahmemodus"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:200
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:206
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:201
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:207
 msgid "OpenAI API Key Test"
 msgstr "OpenAI-API-Schlüssel Test"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:201
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:202
 msgid ""
 "Your API key is valid. Buzz will use this key to perform Whisper API "
 "transcriptions and AI translations."
@@ -173,11 +178,11 @@ msgstr ""
 "Ihr API-Schlüssel ist gültig. Buzz verwendet diesen Schlüssel, um Whisper-"
 "API-Transkriptionen und KI-Übersetzungen durchzuführen."
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:217
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:218
 msgid "Invalid API key"
 msgstr "Ungültiger API-Schlüssel"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:218
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:219
 msgid ""
 "API supports only base64 characters (A-Za-z0-9+/=_-). Other characters in "
 "API key may cause errors."
@@ -185,11 +190,11 @@ msgstr ""
 "Die API unterstützt nur Base64-Zeichen (A-Za-z0-9+/=_-). Andere Zeichen im "
 "API-Schlüssel können Fehler verursachen."
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:236
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:237
 msgid "Select Export Folder"
 msgstr "Exportordner auswählen"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:296
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:297
 msgid ""
 "OpenAI API returned invalid response. Please check the API url or your key. "
 "Transcription and translation may still work if the API does not support key "
@@ -523,56 +528,131 @@ msgstr "Anzeigen"
 msgid "Timestamps"
 msgstr "Zeitstempel"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:146
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:150
 msgid "Export"
 msgstr "Export"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:160
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:164
 #: buzz/transcriber/transcriber.py:24
 msgid "Translate"
 msgstr "Übersetzen"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:170
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:168
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:174
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:166
 msgid "Resize"
 msgstr "Größe ändern"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:269
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:187
+msgid "Identify Speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:286
 msgid "API Key Required"
 msgstr "API-Schlüssel erforderlich"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:270
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:287
 msgid "Please enter OpenAI API Key in preferences"
 msgstr "Bitte geben Sie den OpenAI-API-Schlüssel in den Einstellungen ein"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:150
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:148
 msgid "Resize Options"
 msgstr "Größenänderungsoptionen"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:161
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:159
 msgid "Desired subtitle length"
 msgstr "Gewünschte Untertitellänge"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:186
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:184
 msgid "Merge Options"
 msgstr "Zusammenführungsoptionen"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:197
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:195
 msgid "Merge by gap"
 msgstr "Nach Abstand zusammenführen"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:205
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:203
 msgid "Split by punctuation"
 msgstr "Durch Satzzeichen getrennt"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:213
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:211
 msgid "Split by max length"
 msgstr "Aufgeteilt nach maximaler Länge"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:225
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:223
 msgid "Merge"
 msgstr "Vereinigen"
 
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:101
+msgid "1/9 Collecting transcripts"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:115
+msgid "2/9 Loading audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:124
+msgid "3/9 Loading alignment model"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:130
+msgid "4/9 Preparing audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:142
+#, fuzzy
+msgid "5/9 Preparing transcripts"
+msgstr "Transkript öffnen"
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:160
+msgid "6/9 Converting audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:174
+msgid "7/9 Identifying speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:184
+msgid "8/9 Mapping speakers to transcripts"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:233
+msgid "9/9 Identification done"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:278
+msgid "Step 1: Identify speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:290
+msgid "Identify"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:300
+msgid "Ready to identify speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:302
+msgid "Audio file not found"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:318
+msgid "Step 2: Name speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:333
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:431
+msgid "Play sample"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:348
+msgid "Merge speaker sentences"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:353
+#, fuzzy
+msgid "Save"
+msgstr "Datei speichern"
+
 #: buzz/widgets/transcription_viewer/export_transcription_menu.py:78
 msgid "Save File"
 msgstr "Datei speichern"
@@ -681,10 +761,6 @@ msgstr "Portugiesisch"
 msgid "Turkish"
 msgstr "Türkisch"
 
-#: buzz/transcriber/transcriber.py:50
-msgid "Dutch"
-msgstr "Niederländisch"
-
 #: buzz/transcriber/transcriber.py:51
 msgid "Arabic"
 msgstr "Arabisch"

buzz/locale/en_US/LC_MESSAGES/buzz.po

@@ -8,7 +8,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: PACKAGE VERSION\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2025-03-06 19:12+0200\n"
+"POT-Creation-Date: 2025-04-06 20:58+0300\n"
 "PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
 "Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
 "Language-Team: LANGUAGE <LL@li.org>\n"
@@ -73,120 +73,125 @@ msgid "Danish"
 msgstr ""
 
 #: buzz/widgets/preferences_dialog/general_preferences_widget.py:38
+#: buzz/transcriber/transcriber.py:50
+msgid "Dutch"
+msgstr ""
+
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:39
 #: buzz/transcriber/transcriber.py:40
 msgid "German"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:39
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:40
 #: buzz/transcriber/transcriber.py:41
 msgid "Spanish"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:40
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:41
 #: buzz/transcriber/transcriber.py:53
 msgid "Italian"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:41
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:42
 #: buzz/transcriber/transcriber.py:45
 msgid "Japanese"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:42
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:43
 #: buzz/transcriber/transcriber.py:80
 msgid "Latvian"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:43
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:44
 #: buzz/transcriber/transcriber.py:48
 msgid "Polish"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:44
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:45
 #: buzz/transcriber/transcriber.py:59
 msgid "Ukrainian"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:45
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:46
 msgid "Chinese (Simplified)"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:46
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:47
 msgid "Chinese (Traditional)"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:84
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:85
 msgid "Restart required!"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:88
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:89
 msgid "Ui Language"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:96
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:97
 msgid "Font Size"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:105
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:106
 msgid "Test"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:111
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:112
 msgid "OpenAI API key"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:124
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:125
 msgid "OpenAI base url"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:133
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:134
 msgid "Default export file name"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:139
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:140
 msgid "Enable live recording transcription export"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:145
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:146
 #: buzz/widgets/preferences_dialog/folder_watch_preferences_widget.py:47
 #: buzz/widgets/preferences_dialog/folder_watch_preferences_widget.py:50
 msgid "Browse"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:164
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:165
 msgid "Export folder"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:175
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:176
 msgid "Live recording mode"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:200
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:206
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:201
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:207
 msgid "OpenAI API Key Test"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:201
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:202
 msgid ""
 "Your API key is valid. Buzz will use this key to perform Whisper API "
 "transcriptions and AI translations."
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:217
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:218
 msgid "Invalid API key"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:218
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:219
 msgid ""
 "API supports only base64 characters (A-Za-z0-9+/=_-). Other characters in "
 "API key may cause errors."
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:236
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:237
 msgid "Select Export Folder"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:296
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:297
 msgid ""
 "OpenAI API returned invalid response. Please check the API url or your key. "
 "Transcription and translation may still work if the API does not support key "
@@ -512,56 +517,129 @@ msgstr ""
 msgid "Timestamps"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:146
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:150
 msgid "Export"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:160
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:164
 #: buzz/transcriber/transcriber.py:24
 msgid "Translate"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:170
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:168
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:174
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:166
 msgid "Resize"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:269
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:187
+msgid "Identify Speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:286
 msgid "API Key Required"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:270
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:287
 msgid "Please enter OpenAI API Key in preferences"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:150
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:148
 msgid "Resize Options"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:161
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:159
 msgid "Desired subtitle length"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:186
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:184
 msgid "Merge Options"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:197
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:195
 msgid "Merge by gap"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:205
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:203
 msgid "Split by punctuation"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:213
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:211
 msgid "Split by max length"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:225
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:223
 msgid "Merge"
 msgstr ""
 
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:101
+msgid "1/9 Collecting transcripts"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:115
+msgid "2/9 Loading audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:124
+msgid "3/9 Loading alignment model"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:130
+msgid "4/9 Preparing audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:142
+msgid "5/9 Preparing transcripts"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:160
+msgid "6/9 Converting audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:174
+msgid "7/9 Identifying speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:184
+msgid "8/9 Mapping speakers to transcripts"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:233
+msgid "9/9 Identification done"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:278
+msgid "Step 1: Identify speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:290
+msgid "Identify"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:300
+msgid "Ready to identify speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:302
+msgid "Audio file not found"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:318
+msgid "Step 2: Name speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:333
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:431
+msgid "Play sample"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:348
+msgid "Merge speaker sentences"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:353
+msgid "Save"
+msgstr ""
+
 #: buzz/widgets/transcription_viewer/export_transcription_menu.py:78
 msgid "Save File"
 msgstr ""
@@ -663,10 +741,6 @@ msgstr ""
 msgid "Turkish"
 msgstr ""
 
-#: buzz/transcriber/transcriber.py:50
-msgid "Dutch"
-msgstr ""
-
 #: buzz/transcriber/transcriber.py:51
 msgid "Arabic"
 msgstr ""

buzz/locale/es_ES/LC_MESSAGES/buzz.po

@@ -7,7 +7,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: \n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2025-03-06 19:12+0200\n"
+"POT-Creation-Date: 2025-04-06 20:58+0300\n"
 "PO-Revision-Date: 2023-11-09 04:35-0600\n"
 "Last-Translator: Adolfo Jayme Barrientos <fitojb@ubuntu.com>\n"
 "Language-Team: \n"
@@ -74,124 +74,129 @@ msgid "Danish"
 msgstr ""
 
 #: buzz/widgets/preferences_dialog/general_preferences_widget.py:38
+#: buzz/transcriber/transcriber.py:50
+msgid "Dutch"
+msgstr ""
+
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:39
 #: buzz/transcriber/transcriber.py:40
 msgid "German"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:39
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:40
 #: buzz/transcriber/transcriber.py:41
 msgid "Spanish"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:40
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:41
 #: buzz/transcriber/transcriber.py:53
 msgid "Italian"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:41
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:42
 #: buzz/transcriber/transcriber.py:45
 msgid "Japanese"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:42
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:43
 #: buzz/transcriber/transcriber.py:80
 msgid "Latvian"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:43
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:44
 #: buzz/transcriber/transcriber.py:48
 msgid "Polish"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:44
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:45
 #: buzz/transcriber/transcriber.py:59
 msgid "Ukrainian"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:45
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:46
 msgid "Chinese (Simplified)"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:46
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:47
 msgid "Chinese (Traditional)"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:84
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:85
 msgid "Restart required!"
 msgstr ""
 
 # automatic translation
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:88
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:89
 #, fuzzy
 msgid "Ui Language"
 msgstr "Idioma:"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:96
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:97
 msgid "Font Size"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:105
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:106
 msgid "Test"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:111
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:112
 msgid "OpenAI API key"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:124
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:125
 msgid "OpenAI base url"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:133
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:134
 msgid "Default export file name"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:139
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:140
 msgid "Enable live recording transcription export"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:145
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:146
 #: buzz/widgets/preferences_dialog/folder_watch_preferences_widget.py:47
 #: buzz/widgets/preferences_dialog/folder_watch_preferences_widget.py:50
 msgid "Browse"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:164
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:165
 msgid "Export folder"
 msgstr ""
 
 # automatic translation
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:175
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:176
 #, fuzzy
 msgid "Live recording mode"
 msgstr "Grabación en vivo"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:200
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:206
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:201
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:207
 msgid "OpenAI API Key Test"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:201
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:202
 msgid ""
 "Your API key is valid. Buzz will use this key to perform Whisper API "
 "transcriptions and AI translations."
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:217
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:218
 msgid "Invalid API key"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:218
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:219
 msgid ""
 "API supports only base64 characters (A-Za-z0-9+/=_-). Other characters in "
 "API key may cause errors."
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:236
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:237
 msgid "Select Export Folder"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:296
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:297
 msgid ""
 "OpenAI API returned invalid response. Please check the API url or your key. "
 "Transcription and translation may still work if the API does not support key "
@@ -563,56 +568,133 @@ msgstr ""
 msgid "Timestamps"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:146
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:150
 msgid "Export"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:160
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:164
 #: buzz/transcriber/transcriber.py:24
 msgid "Translate"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:170
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:168
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:174
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:166
 msgid "Resize"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:269
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:187
+msgid "Identify Speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:286
 msgid "API Key Required"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:270
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:287
 msgid "Please enter OpenAI API Key in preferences"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:150
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:148
 msgid "Resize Options"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:161
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:159
 msgid "Desired subtitle length"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:186
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:184
 msgid "Merge Options"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:197
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:195
 msgid "Merge by gap"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:205
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:203
 msgid "Split by punctuation"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:213
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:211
 msgid "Split by max length"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:225
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:223
 msgid "Merge"
 msgstr ""
 
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:101
+msgid "1/9 Collecting transcripts"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:115
+msgid "2/9 Loading audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:124
+msgid "3/9 Loading alignment model"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:130
+msgid "4/9 Preparing audio"
+msgstr ""
+
+# automatic translation
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:142
+#, fuzzy
+msgid "5/9 Preparing transcripts"
+msgstr "Abrir transcripción"
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:160
+msgid "6/9 Converting audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:174
+msgid "7/9 Identifying speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:184
+msgid "8/9 Mapping speakers to transcripts"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:233
+msgid "9/9 Identification done"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:278
+msgid "Step 1: Identify speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:290
+msgid "Identify"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:300
+msgid "Ready to identify speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:302
+msgid "Audio file not found"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:318
+msgid "Step 2: Name speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:333
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:431
+msgid "Play sample"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:348
+msgid "Merge speaker sentences"
+msgstr ""
+
+# automatic translation
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:353
+#, fuzzy
+msgid "Save"
+msgstr "Guardar archivo"
+
 # automatic translation
 #: buzz/widgets/transcription_viewer/export_transcription_menu.py:78
 msgid "Save File"
@@ -729,10 +811,6 @@ msgstr ""
 msgid "Turkish"
 msgstr ""
 
-#: buzz/transcriber/transcriber.py:50
-msgid "Dutch"
-msgstr ""
-
 #: buzz/transcriber/transcriber.py:51
 msgid "Arabic"
 msgstr ""

buzz/locale/it_IT/LC_MESSAGES/buzz.po

@@ -6,7 +6,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: buzz\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2025-03-06 19:12+0200\n"
+"POT-Creation-Date: 2025-04-06 20:58+0300\n"
 "PO-Revision-Date: 2024-11-24 13:22+0100\n"
 "Language-Team: (Italiano) Albano Battistella <albanobattistella@gmail.com>\n"
 "Language: it_IT\n"
@@ -72,102 +72,107 @@ msgid "Danish"
 msgstr ""
 
 #: buzz/widgets/preferences_dialog/general_preferences_widget.py:38
+#: buzz/transcriber/transcriber.py:50
+msgid "Dutch"
+msgstr ""
+
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:39
 #: buzz/transcriber/transcriber.py:40
 msgid "German"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:39
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:40
 #: buzz/transcriber/transcriber.py:41
 msgid "Spanish"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:40
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:41
 #: buzz/transcriber/transcriber.py:53
 msgid "Italian"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:41
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:42
 #: buzz/transcriber/transcriber.py:45
 msgid "Japanese"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:42
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:43
 #: buzz/transcriber/transcriber.py:80
 msgid "Latvian"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:43
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:44
 #: buzz/transcriber/transcriber.py:48
 msgid "Polish"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:44
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:45
 #: buzz/transcriber/transcriber.py:59
 #, fuzzy
 msgid "Ukrainian"
 msgstr "rimanente"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:45
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:46
 msgid "Chinese (Simplified)"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:46
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:47
 msgid "Chinese (Traditional)"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:84
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:85
 msgid "Restart required!"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:88
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:89
 #, fuzzy
 msgid "Ui Language"
 msgstr "Lingua:"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:96
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:97
 msgid "Font Size"
 msgstr "Dimensione del carattere"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:105
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:106
 msgid "Test"
 msgstr "Test"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:111
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:112
 msgid "OpenAI API key"
 msgstr "Chiave API OpenAI"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:124
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:125
 msgid "OpenAI base url"
 msgstr "URL di base di OpenAI"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:133
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:134
 msgid "Default export file name"
 msgstr "Nome file di esportazione predefinito"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:139
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:140
 msgid "Enable live recording transcription export"
 msgstr "Abilita l'esportazione della trascrizione della registrazione live"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:145
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:146
 #: buzz/widgets/preferences_dialog/folder_watch_preferences_widget.py:47
 #: buzz/widgets/preferences_dialog/folder_watch_preferences_widget.py:50
 msgid "Browse"
 msgstr "Sfoglia"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:164
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:165
 msgid "Export folder"
 msgstr "Esporta cartella"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:175
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:176
 msgid "Live recording mode"
 msgstr "Modalità di registrazione in diretta"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:200
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:206
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:201
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:207
 msgid "OpenAI API Key Test"
 msgstr "Test della chiave API OpenAI"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:201
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:202
 msgid ""
 "Your API key is valid. Buzz will use this key to perform Whisper API "
 "transcriptions and AI translations."
@@ -175,11 +180,11 @@ msgstr ""
 "La tua chiave API è valida. Buzz utilizzerà questa chiave per eseguire le "
 "trascrizioni API Whisper e le traduzioni AI."
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:217
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:218
 msgid "Invalid API key"
 msgstr "Chiave API non valida"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:218
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:219
 #, fuzzy
 msgid ""
 "API supports only base64 characters (A-Za-z0-9+/=_-). Other characters in "
@@ -188,11 +193,11 @@ msgstr ""
 "L'API supporta solo caratteri base64 (A-Za-z0-9+/=). Altri caratteri nella "
 "chiave API potrebbero causare errori."
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:236
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:237
 msgid "Select Export Folder"
 msgstr "Seleziona la cartella di esportazione"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:296
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:297
 msgid ""
 "OpenAI API returned invalid response. Please check the API url or your key. "
 "Transcription and translation may still work if the API does not support key "
@@ -525,57 +530,132 @@ msgstr "Visualizza"
 msgid "Timestamps"
 msgstr "Timestamp"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:146
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:150
 msgid "Export"
 msgstr "Esporta"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:160
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:164
 #: buzz/transcriber/transcriber.py:24
 msgid "Translate"
 msgstr "Tradurre"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:170
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:168
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:174
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:166
 msgid "Resize"
 msgstr "Ridimensionare"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:269
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:187
+msgid "Identify Speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:286
 msgid "API Key Required"
 msgstr "Chiave API richiesta"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:270
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:287
 msgid "Please enter OpenAI API Key in preferences"
 msgstr "Inserisci la chiave API OpenAI nelle preferenze"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:150
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:148
 #, fuzzy
 msgid "Resize Options"
 msgstr "Ridimensionare"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:161
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:159
 msgid "Desired subtitle length"
 msgstr "Lunghezza desiderata dei sottotitoli"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:186
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:184
 msgid "Merge Options"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:197
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:195
 msgid "Merge by gap"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:205
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:203
 msgid "Split by punctuation"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:213
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:211
 msgid "Split by max length"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:225
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:223
 msgid "Merge"
 msgstr ""
 
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:101
+msgid "1/9 Collecting transcripts"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:115
+msgid "2/9 Loading audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:124
+msgid "3/9 Loading alignment model"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:130
+msgid "4/9 Preparing audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:142
+#, fuzzy
+msgid "5/9 Preparing transcripts"
+msgstr "Apri trascrizione"
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:160
+msgid "6/9 Converting audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:174
+msgid "7/9 Identifying speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:184
+msgid "8/9 Mapping speakers to transcripts"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:233
+msgid "9/9 Identification done"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:278
+msgid "Step 1: Identify speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:290
+msgid "Identify"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:300
+msgid "Ready to identify speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:302
+msgid "Audio file not found"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:318
+msgid "Step 2: Name speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:333
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:431
+msgid "Play sample"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:348
+msgid "Merge speaker sentences"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:353
+#, fuzzy
+msgid "Save"
+msgstr "Salva file"
+
 #: buzz/widgets/transcription_viewer/export_transcription_menu.py:78
 msgid "Save File"
 msgstr "Salva file"
@@ -683,10 +763,6 @@ msgstr ""
 msgid "Turkish"
 msgstr ""
 
-#: buzz/transcriber/transcriber.py:50
-msgid "Dutch"
-msgstr ""
-
 #: buzz/transcriber/transcriber.py:51
 msgid "Arabic"
 msgstr ""

buzz/locale/ja_JP/LC_MESSAGES/buzz.po

@@ -2,7 +2,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: \n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2025-03-06 19:12+0200\n"
+"POT-Creation-Date: 2025-04-06 20:58+0300\n"
 "PO-Revision-Date: \n"
 "Last-Translator: nunawa <71294849+nunawa@users.noreply.github.com>\n"
 "Language-Team: \n"
@@ -68,103 +68,108 @@ msgid "Danish"
 msgstr ""
 
 #: buzz/widgets/preferences_dialog/general_preferences_widget.py:38
+#: buzz/transcriber/transcriber.py:50
+msgid "Dutch"
+msgstr ""
+
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:39
 #: buzz/transcriber/transcriber.py:40
 msgid "German"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:39
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:40
 #: buzz/transcriber/transcriber.py:41
 msgid "Spanish"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:40
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:41
 #: buzz/transcriber/transcriber.py:53
 msgid "Italian"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:41
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:42
 #: buzz/transcriber/transcriber.py:45
 msgid "Japanese"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:42
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:43
 #: buzz/transcriber/transcriber.py:80
 msgid "Latvian"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:43
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:44
 #: buzz/transcriber/transcriber.py:48
 msgid "Polish"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:44
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:45
 #: buzz/transcriber/transcriber.py:59
 #, fuzzy
 msgid "Ukrainian"
 msgstr "残り"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:45
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:46
 msgid "Chinese (Simplified)"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:46
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:47
 msgid "Chinese (Traditional)"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:84
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:85
 msgid "Restart required!"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:88
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:89
 #, fuzzy
 msgid "Ui Language"
 msgstr "言語:"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:96
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:97
 msgid "Font Size"
 msgstr "フォントサイズ"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:105
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:106
 msgid "Test"
 msgstr "テスト"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:111
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:112
 msgid "OpenAI API key"
 msgstr "OpenAI APIキー"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:124
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:125
 msgid "OpenAI base url"
 msgstr "OpenAI ベースURL"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:133
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:134
 msgid "Default export file name"
 msgstr "デフォルトの出力ファイル名"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:139
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:140
 msgid "Enable live recording transcription export"
 msgstr "ライブ録音書き起こしの出力を有効にする"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:145
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:146
 #: buzz/widgets/preferences_dialog/folder_watch_preferences_widget.py:47
 #: buzz/widgets/preferences_dialog/folder_watch_preferences_widget.py:50
 msgid "Browse"
 msgstr "参照"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:164
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:165
 msgid "Export folder"
 msgstr "出力フォルダ"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:175
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:176
 #, fuzzy
 msgid "Live recording mode"
 msgstr "ライブ録音"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:200
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:206
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:201
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:207
 msgid "OpenAI API Key Test"
 msgstr "OpenAI APIキー テスト"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:201
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:202
 msgid ""
 "Your API key is valid. Buzz will use this key to perform Whisper API "
 "transcriptions and AI translations."
@@ -172,22 +177,22 @@ msgstr ""
 "あなたのAPIキーは有効です。Buzzはこのキーを使ってWhisper APIの書き起こしとAI"
 "翻訳を行います。"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:217
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:218
 #, fuzzy
 msgid "Invalid API key"
 msgstr "OpenAI APIキー"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:218
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:219
 msgid ""
 "API supports only base64 characters (A-Za-z0-9+/=_-). Other characters in "
 "API key may cause errors."
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:236
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:237
 msgid "Select Export Folder"
 msgstr "出力フォルダを選択"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:296
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:297
 msgid ""
 "OpenAI API returned invalid response. Please check the API url or your key. "
 "Transcription and translation may still work if the API does not support key "
@@ -520,57 +525,132 @@ msgstr "表示"
 msgid "Timestamps"
 msgstr "タイムスタンプ"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:146
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:150
 msgid "Export"
 msgstr "出力"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:160
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:164
 #: buzz/transcriber/transcriber.py:24
 msgid "Translate"
 msgstr "翻訳"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:170
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:168
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:174
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:166
 msgid "Resize"
 msgstr "リサイズ"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:269
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:187
+msgid "Identify Speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:286
 msgid "API Key Required"
 msgstr "APIキーが必要"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:270
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:287
 msgid "Please enter OpenAI API Key in preferences"
 msgstr "設定画面でOpenAI APIキーを入力してください"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:150
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:148
 #, fuzzy
 msgid "Resize Options"
 msgstr "リサイズ"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:161
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:159
 msgid "Desired subtitle length"
 msgstr "希望する字幕の長さ"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:186
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:184
 msgid "Merge Options"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:197
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:195
 msgid "Merge by gap"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:205
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:203
 msgid "Split by punctuation"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:213
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:211
 msgid "Split by max length"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:225
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:223
 msgid "Merge"
 msgstr ""
 
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:101
+msgid "1/9 Collecting transcripts"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:115
+msgid "2/9 Loading audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:124
+msgid "3/9 Loading alignment model"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:130
+msgid "4/9 Preparing audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:142
+#, fuzzy
+msgid "5/9 Preparing transcripts"
+msgstr "文字起こしを開く"
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:160
+msgid "6/9 Converting audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:174
+msgid "7/9 Identifying speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:184
+msgid "8/9 Mapping speakers to transcripts"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:233
+msgid "9/9 Identification done"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:278
+msgid "Step 1: Identify speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:290
+msgid "Identify"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:300
+msgid "Ready to identify speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:302
+msgid "Audio file not found"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:318
+msgid "Step 2: Name speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:333
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:431
+msgid "Play sample"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:348
+msgid "Merge speaker sentences"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:353
+#, fuzzy
+msgid "Save"
+msgstr "ファイルを保存"
+
 #: buzz/widgets/transcription_viewer/export_transcription_menu.py:78
 msgid "Save File"
 msgstr "ファイルを保存"
@@ -676,10 +756,6 @@ msgstr ""
 msgid "Turkish"
 msgstr ""
 
-#: buzz/transcriber/transcriber.py:50
-msgid "Dutch"
-msgstr ""
-
 #: buzz/transcriber/transcriber.py:51
 msgid "Arabic"
 msgstr ""

buzz/locale/lv_LV/LC_MESSAGES/buzz.po

@@ -8,8 +8,8 @@ msgid ""
 msgstr ""
 "Project-Id-Version: \n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2025-03-06 19:12+0200\n"
-"PO-Revision-Date: 2025-02-22 23:44+0200\n"
+"POT-Creation-Date: 2025-04-06 20:58+0300\n"
+"PO-Revision-Date: 2025-04-06 21:04+0300\n"
 "Last-Translator: \n"
 "Language-Team: \n"
 "Language: lv_LV\n"
@@ -74,102 +74,107 @@ msgid "Danish"
 msgstr "Dāņu"
 
 #: buzz/widgets/preferences_dialog/general_preferences_widget.py:38
+#: buzz/transcriber/transcriber.py:50
+msgid "Dutch"
+msgstr "Holandiešu"
+
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:39
 #: buzz/transcriber/transcriber.py:40
 msgid "German"
 msgstr "Vācu"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:39
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:40
 #: buzz/transcriber/transcriber.py:41
 msgid "Spanish"
 msgstr "Spāņu"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:40
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:41
 #: buzz/transcriber/transcriber.py:53
 msgid "Italian"
 msgstr "Itāļu"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:41
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:42
 #: buzz/transcriber/transcriber.py:45
 msgid "Japanese"
 msgstr "Japāņu"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:42
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:43
 #: buzz/transcriber/transcriber.py:80
 msgid "Latvian"
 msgstr "Latviešu"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:43
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:44
 #: buzz/transcriber/transcriber.py:48
 msgid "Polish"
 msgstr "Poļu"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:44
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:45
 #: buzz/transcriber/transcriber.py:59
 msgid "Ukrainian"
 msgstr "Ukraiņu"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:45
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:46
 msgid "Chinese (Simplified)"
 msgstr "Ķīniešu (vienkāršotā)"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:46
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:47
 msgid "Chinese (Traditional)"
 msgstr "Ķīniešu (tradicionālā)"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:84
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:85
 msgid "Restart required!"
 msgstr "Jāpārstartē!"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:88
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:89
 msgid "Ui Language"
 msgstr "Programmas valoda"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:96
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:97
 msgid "Font Size"
 msgstr "Fonta izmērs"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:105
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:106
 msgid "Test"
 msgstr "Pārbaudīt"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:111
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:112
 msgid "OpenAI API key"
 msgstr "OpenAI API atslēga"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:124
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:125
 msgid "OpenAI base url"
 msgstr "OpenAI adrese"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:133
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:134
 msgid "Default export file name"
 msgstr "Eksporta fails"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:139
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:140
 msgid "Enable live recording transcription export"
 msgstr "Eksportēt dzīvā ieraksta transkriptus"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:145
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:146
 #: buzz/widgets/preferences_dialog/folder_watch_preferences_widget.py:47
 #: buzz/widgets/preferences_dialog/folder_watch_preferences_widget.py:50
 msgid "Browse"
 msgstr "Izvēlēties"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:164
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:165
 msgid "Export folder"
 msgstr "Eksportēt mapē"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:175
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:176
 msgid "Live recording mode"
 msgstr ""
 "Dzīvā ieraksta\n"
 "režīms"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:200
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:206
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:201
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:207
 msgid "OpenAI API Key Test"
 msgstr "OpenAI API atslēgas pārbaude"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:201
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:202
 msgid ""
 "Your API key is valid. Buzz will use this key to perform Whisper API "
 "transcriptions and AI translations."
@@ -177,11 +182,11 @@ msgstr ""
 "Jūsu API atslēga ir derīga. Buzz izmantos to runas atpazīšanai ar Whisper "
 "API un tulkošanai."
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:217
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:218
 msgid "Invalid API key"
 msgstr "Nederīga API atslēga"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:218
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:219
 msgid ""
 "API supports only base64 characters (A-Za-z0-9+/=_-). Other characters in "
 "API key may cause errors."
@@ -189,11 +194,11 @@ msgstr ""
 "API atbalsta tikai base64 simbolus (A-Za-z0-9+/=_-). Citi simboli API "
 "atslēgā var radīt kļūdas."
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:236
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:237
 msgid "Select Export Folder"
 msgstr "Izvēlieties mapi kurā eksportēt"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:296
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:297
 msgid ""
 "OpenAI API returned invalid response. Please check the API url or your key. "
 "Transcription and translation may still work if the API does not support key "
@@ -526,56 +531,129 @@ msgstr "Skats"
 msgid "Timestamps"
 msgstr "Laiks"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:146
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:150
 msgid "Export"
 msgstr "Eksportēt"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:160
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:164
 #: buzz/transcriber/transcriber.py:24
 msgid "Translate"
 msgstr "Tulkot"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:170
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:168
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:174
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:166
 msgid "Resize"
 msgstr "Mainīt garumu"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:269
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:187
+msgid "Identify Speakers"
+msgstr "Noteikt runātājus"
+
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:286
 msgid "API Key Required"
 msgstr "API atslēgas kļūda"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:270
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:287
 msgid "Please enter OpenAI API Key in preferences"
 msgstr "Lūdzu ievadiet OpenAI API atslēgu iestatījumos"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:150
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:148
 msgid "Resize Options"
 msgstr "Garuma maiņas iestatījumi"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:161
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:159
 msgid "Desired subtitle length"
 msgstr "Vēlamais teksta garums"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:186
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:184
 msgid "Merge Options"
 msgstr "Apvienošanas iestatījumi"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:197
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:195
 msgid "Merge by gap"
 msgstr "Apvienot pēc attāluma"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:205
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:203
 msgid "Split by punctuation"
 msgstr "Dalīt pie pieturzīmēm"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:213
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:211
 msgid "Split by max length"
 msgstr "Dalīt pie maksimālā garuma"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:225
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:223
 msgid "Merge"
 msgstr "Apvienot"
 
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:101
+msgid "1/9 Collecting transcripts"
+msgstr "1/9 Apkopo transkripcijas"
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:115
+msgid "2/9 Loading audio"
+msgstr "2/9 Ielādē audio"
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:124
+msgid "3/9 Loading alignment model"
+msgstr "3/9 Ielādē identifikācijas modeli"
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:130
+msgid "4/9 Preparing audio"
+msgstr "4/9 Sagatavo audio"
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:142
+msgid "5/9 Preparing transcripts"
+msgstr "5/9 Sagatavo transkripcijas"
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:160
+msgid "6/9 Converting audio"
+msgstr "6/9 Apstrādā audio"
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:174
+msgid "7/9 Identifying speakers"
+msgstr "7/9 Nosaka runātājus"
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:184
+msgid "8/9 Mapping speakers to transcripts"
+msgstr "8/9 Marķē runātāju teikumus"
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:233
+msgid "9/9 Identification done"
+msgstr "9/9 Runātāju noteikšana pabeigta"
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:278
+msgid "Step 1: Identify speakers"
+msgstr "1. solis: Runātāju noteikšana"
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:290
+msgid "Identify"
+msgstr "Noteikt"
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:300
+msgid "Ready to identify speakers"
+msgstr "Gatavs noteikt runātājus"
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:302
+msgid "Audio file not found"
+msgstr "Audio datne nav atrasta"
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:318
+msgid "Step 2: Name speakers"
+msgstr "2. solis: Identificēt runātājus"
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:333
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:431
+msgid "Play sample"
+msgstr "Atskaņot paraugu"
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:348
+msgid "Merge speaker sentences"
+msgstr "Apvienot runātāja teikumus"
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:353
+msgid "Save"
+msgstr "Saglabāt"
+
 #: buzz/widgets/transcription_viewer/export_transcription_menu.py:78
 msgid "Save File"
 msgstr "Saglabāt failu"
@@ -681,10 +759,6 @@ msgstr "Portugāļu"
 msgid "Turkish"
 msgstr "Turku"
 
-#: buzz/transcriber/transcriber.py:50
-msgid "Dutch"
-msgstr "Holandiešu"
-
 #: buzz/transcriber/transcriber.py:51
 msgid "Arabic"
 msgstr "Arābu"

buzz/locale/pl_PL/LC_MESSAGES/buzz.po

@@ -7,7 +7,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: \n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2025-03-06 19:12+0200\n"
+"POT-Creation-Date: 2025-04-06 20:58+0300\n"
 "PO-Revision-Date: 2024-03-17 20:50+0200\n"
 "Last-Translator: \n"
 "Language-Team: \n"
@@ -73,123 +73,128 @@ msgid "Danish"
 msgstr ""
 
 #: buzz/widgets/preferences_dialog/general_preferences_widget.py:38
+#: buzz/transcriber/transcriber.py:50
+msgid "Dutch"
+msgstr ""
+
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:39
 #: buzz/transcriber/transcriber.py:40
 msgid "German"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:39
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:40
 #: buzz/transcriber/transcriber.py:41
 msgid "Spanish"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:40
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:41
 #: buzz/transcriber/transcriber.py:53
 msgid "Italian"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:41
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:42
 #: buzz/transcriber/transcriber.py:45
 msgid "Japanese"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:42
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:43
 #: buzz/transcriber/transcriber.py:80
 msgid "Latvian"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:43
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:44
 #: buzz/transcriber/transcriber.py:48
 msgid "Polish"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:44
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:45
 #: buzz/transcriber/transcriber.py:59
 msgid "Ukrainian"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:45
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:46
 msgid "Chinese (Simplified)"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:46
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:47
 msgid "Chinese (Traditional)"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:84
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:85
 msgid "Restart required!"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:88
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:89
 #, fuzzy
 msgid "Ui Language"
 msgstr "Język:"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:96
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:97
 msgid "Font Size"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:105
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:106
 msgid "Test"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:111
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:112
 msgid "OpenAI API key"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:124
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:125
 msgid "OpenAI base url"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:133
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:134
 msgid "Default export file name"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:139
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:140
 msgid "Enable live recording transcription export"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:145
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:146
 #: buzz/widgets/preferences_dialog/folder_watch_preferences_widget.py:47
 #: buzz/widgets/preferences_dialog/folder_watch_preferences_widget.py:50
 msgid "Browse"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:164
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:165
 msgid "Export folder"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:175
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:176
 #, fuzzy
 msgid "Live recording mode"
 msgstr "Nagrywanie na żywo"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:200
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:206
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:201
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:207
 msgid "OpenAI API Key Test"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:201
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:202
 msgid ""
 "Your API key is valid. Buzz will use this key to perform Whisper API "
 "transcriptions and AI translations."
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:217
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:218
 #, fuzzy
 msgid "Invalid API key"
 msgstr "Nieprawidłowy URL"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:218
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:219
 msgid ""
 "API supports only base64 characters (A-Za-z0-9+/=_-). Other characters in "
 "API key may cause errors."
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:236
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:237
 msgid "Select Export Folder"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:296
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:297
 msgid ""
 "OpenAI API returned invalid response. Please check the API url or your key. "
 "Transcription and translation may still work if the API does not support key "
@@ -533,56 +538,131 @@ msgstr ""
 msgid "Timestamps"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:146
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:150
 msgid "Export"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:160
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:164
 #: buzz/transcriber/transcriber.py:24
 msgid "Translate"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:170
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:168
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:174
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:166
 msgid "Resize"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:269
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:187
+msgid "Identify Speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:286
 msgid "API Key Required"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:270
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:287
 msgid "Please enter OpenAI API Key in preferences"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:150
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:148
 msgid "Resize Options"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:161
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:159
 msgid "Desired subtitle length"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:186
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:184
 msgid "Merge Options"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:197
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:195
 msgid "Merge by gap"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:205
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:203
 msgid "Split by punctuation"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:213
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:211
 msgid "Split by max length"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:225
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:223
 msgid "Merge"
 msgstr ""
 
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:101
+msgid "1/9 Collecting transcripts"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:115
+msgid "2/9 Loading audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:124
+msgid "3/9 Loading alignment model"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:130
+msgid "4/9 Preparing audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:142
+#, fuzzy
+msgid "5/9 Preparing transcripts"
+msgstr "Otwórz transkrypt"
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:160
+msgid "6/9 Converting audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:174
+msgid "7/9 Identifying speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:184
+msgid "8/9 Mapping speakers to transcripts"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:233
+msgid "9/9 Identification done"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:278
+msgid "Step 1: Identify speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:290
+msgid "Identify"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:300
+msgid "Ready to identify speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:302
+msgid "Audio file not found"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:318
+msgid "Step 2: Name speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:333
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:431
+msgid "Play sample"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:348
+msgid "Merge speaker sentences"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:353
+#, fuzzy
+msgid "Save"
+msgstr "Zapisz plik"
+
 #: buzz/widgets/transcription_viewer/export_transcription_menu.py:78
 #, fuzzy
 msgid "Save File"
@@ -691,10 +771,6 @@ msgstr ""
 msgid "Turkish"
 msgstr ""
 
-#: buzz/transcriber/transcriber.py:50
-msgid "Dutch"
-msgstr ""
-
 #: buzz/transcriber/transcriber.py:51
 msgid "Arabic"
 msgstr ""

buzz/locale/uk_UA/LC_MESSAGES/buzz.po

@@ -2,7 +2,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: \n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2025-03-06 19:12+0200\n"
+"POT-Creation-Date: 2025-04-06 20:58+0300\n"
 "PO-Revision-Date: \n"
 "Last-Translator: Yevhen Popok <xalt7x.service@gmail.com>\n"
 "Language-Team: \n"
@@ -70,103 +70,108 @@ msgid "Danish"
 msgstr ""
 
 #: buzz/widgets/preferences_dialog/general_preferences_widget.py:38
+#: buzz/transcriber/transcriber.py:50
+msgid "Dutch"
+msgstr ""
+
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:39
 #: buzz/transcriber/transcriber.py:40
 msgid "German"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:39
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:40
 #: buzz/transcriber/transcriber.py:41
 msgid "Spanish"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:40
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:41
 #: buzz/transcriber/transcriber.py:53
 msgid "Italian"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:41
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:42
 #: buzz/transcriber/transcriber.py:45
 msgid "Japanese"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:42
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:43
 #: buzz/transcriber/transcriber.py:80
 msgid "Latvian"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:43
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:44
 #: buzz/transcriber/transcriber.py:48
 msgid "Polish"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:44
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:45
 #: buzz/transcriber/transcriber.py:59
 #, fuzzy
 msgid "Ukrainian"
 msgstr "залишилось"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:45
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:46
 msgid "Chinese (Simplified)"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:46
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:47
 msgid "Chinese (Traditional)"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:84
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:85
 msgid "Restart required!"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:88
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:89
 #, fuzzy
 msgid "Ui Language"
 msgstr "Мова:"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:96
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:97
 msgid "Font Size"
 msgstr "Розмір шрифту"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:105
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:106
 msgid "Test"
 msgstr "Тест"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:111
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:112
 msgid "OpenAI API key"
 msgstr "API-ключ OpenAI"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:124
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:125
 msgid "OpenAI base url"
 msgstr "Базова адреса OpenAI"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:133
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:134
 msgid "Default export file name"
 msgstr "Типова назва файлу експорту"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:139
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:140
 msgid "Enable live recording transcription export"
 msgstr "Увімкнути експорт транскрипції з живого запису"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:145
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:146
 #: buzz/widgets/preferences_dialog/folder_watch_preferences_widget.py:47
 #: buzz/widgets/preferences_dialog/folder_watch_preferences_widget.py:50
 msgid "Browse"
 msgstr "Огляд"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:164
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:165
 msgid "Export folder"
 msgstr "Тека для експорту"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:175
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:176
 #, fuzzy
 msgid "Live recording mode"
 msgstr "Живий запис"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:200
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:206
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:201
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:207
 msgid "OpenAI API Key Test"
 msgstr "Тест API-ключа OpenAI"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:201
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:202
 msgid ""
 "Your API key is valid. Buzz will use this key to perform Whisper API "
 "transcriptions and AI translations."
@@ -174,22 +179,22 @@ msgstr ""
 "Ваш API-ключ дійсний. Buzz використає цей ключ для транскрипції з Whisper "
 "API та перекладу ШІ."
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:217
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:218
 #, fuzzy
 msgid "Invalid API key"
 msgstr "API-ключ OpenAI"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:218
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:219
 msgid ""
 "API supports only base64 characters (A-Za-z0-9+/=_-). Other characters in "
 "API key may cause errors."
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:236
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:237
 msgid "Select Export Folder"
 msgstr "Виберіть теку для експорту"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:296
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:297
 msgid ""
 "OpenAI API returned invalid response. Please check the API url or your key. "
 "Transcription and translation may still work if the API does not support key "
@@ -522,56 +527,131 @@ msgstr "Вигляд"
 msgid "Timestamps"
 msgstr "Позначки часу"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:146
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:150
 msgid "Export"
 msgstr "Експорт"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:160
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:164
 #: buzz/transcriber/transcriber.py:24
 msgid "Translate"
 msgstr "Перекласти"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:170
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:168
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:174
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:166
 msgid "Resize"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:269
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:187
+msgid "Identify Speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:286
 msgid "API Key Required"
 msgstr "Потрібен API-ключ"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:270
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:287
 msgid "Please enter OpenAI API Key in preferences"
 msgstr "Будь ласка, введіть API-ключ OpenAI в налаштуваннях"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:150
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:148
 msgid "Resize Options"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:161
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:159
 msgid "Desired subtitle length"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:186
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:184
 msgid "Merge Options"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:197
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:195
 msgid "Merge by gap"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:205
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:203
 msgid "Split by punctuation"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:213
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:211
 msgid "Split by max length"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:225
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:223
 msgid "Merge"
 msgstr ""
 
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:101
+msgid "1/9 Collecting transcripts"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:115
+msgid "2/9 Loading audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:124
+msgid "3/9 Loading alignment model"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:130
+msgid "4/9 Preparing audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:142
+#, fuzzy
+msgid "5/9 Preparing transcripts"
+msgstr "Відкрити транскрипцію"
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:160
+msgid "6/9 Converting audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:174
+msgid "7/9 Identifying speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:184
+msgid "8/9 Mapping speakers to transcripts"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:233
+msgid "9/9 Identification done"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:278
+msgid "Step 1: Identify speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:290
+msgid "Identify"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:300
+msgid "Ready to identify speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:302
+msgid "Audio file not found"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:318
+msgid "Step 2: Name speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:333
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:431
+msgid "Play sample"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:348
+msgid "Merge speaker sentences"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:353
+#, fuzzy
+msgid "Save"
+msgstr "Зберегти файл"
+
 #: buzz/widgets/transcription_viewer/export_transcription_menu.py:78
 msgid "Save File"
 msgstr "Зберегти файл"
@@ -677,10 +757,6 @@ msgstr ""
 msgid "Turkish"
 msgstr ""
 
-#: buzz/transcriber/transcriber.py:50
-msgid "Dutch"
-msgstr ""
-
 #: buzz/transcriber/transcriber.py:51
 msgid "Arabic"
 msgstr ""

buzz/locale/zh_CN/LC_MESSAGES/buzz.po

@@ -7,7 +7,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: \n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2025-03-06 19:12+0200\n"
+"POT-Creation-Date: 2025-04-06 20:58+0300\n"
 "PO-Revision-Date: 2023-05-01 15:45+0800\n"
 "Last-Translator: \n"
 "Language-Team: lamb \n"
@@ -73,113 +73,118 @@ msgid "Danish"
 msgstr ""
 
 #: buzz/widgets/preferences_dialog/general_preferences_widget.py:38
+#: buzz/transcriber/transcriber.py:50
+msgid "Dutch"
+msgstr ""
+
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:39
 #: buzz/transcriber/transcriber.py:40
 msgid "German"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:39
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:40
 #: buzz/transcriber/transcriber.py:41
 msgid "Spanish"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:40
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:41
 #: buzz/transcriber/transcriber.py:53
 msgid "Italian"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:41
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:42
 #: buzz/transcriber/transcriber.py:45
 msgid "Japanese"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:42
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:43
 #: buzz/transcriber/transcriber.py:80
 msgid "Latvian"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:43
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:44
 #: buzz/transcriber/transcriber.py:48
 msgid "Polish"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:44
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:45
 #: buzz/transcriber/transcriber.py:59
 #, fuzzy
 msgid "Ukrainian"
 msgstr "剩余"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:45
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:46
 msgid "Chinese (Simplified)"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:46
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:47
 msgid "Chinese (Traditional)"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:84
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:85
 msgid "Restart required!"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:88
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:89
 #, fuzzy
 msgid "Ui Language"
 msgstr "语言:"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:96
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:97
 msgid "Font Size"
 msgstr "字体大小"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:105
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:106
 msgid "Test"
 msgstr "测试"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:111
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:112
 msgid "OpenAI API key"
 msgstr "OpenAI API key"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:124
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:125
 msgid "OpenAI base url"
 msgstr "OpenAI 基于 url"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:133
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:134
 msgid "Default export file name"
 msgstr "默认输出文件名"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:139
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:140
 msgid "Enable live recording transcription export"
 msgstr "启用实时录制转录导出"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:145
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:146
 #: buzz/widgets/preferences_dialog/folder_watch_preferences_widget.py:47
 #: buzz/widgets/preferences_dialog/folder_watch_preferences_widget.py:50
 msgid "Browse"
 msgstr "浏览"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:164
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:165
 msgid "Export folder"
 msgstr "导出文件夹"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:175
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:176
 #, fuzzy
 msgid "Live recording mode"
 msgstr "现场录制模式"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:200
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:206
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:201
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:207
 msgid "OpenAI API Key Test"
 msgstr "测试OpenAI API Key"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:201
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:202
 msgid ""
 "Your API key is valid. Buzz will use this key to perform Whisper API "
 "transcriptions and AI translations."
 msgstr "您的API密钥有效。Buzz将使用此密钥执行 Whisper API 识别和 AI 翻译。"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:217
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:218
 msgid "Invalid API key"
 msgstr "无效的API key"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:218
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:219
 #, fuzzy
 msgid ""
 "API supports only base64 characters (A-Za-z0-9+/=_-). Other characters in "
@@ -187,11 +192,11 @@ msgid ""
 msgstr ""
 "API只支持 base64字符（A-Za-z0-9+/=）。其他字符在API密钥中可能导致错误。"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:236
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:237
 msgid "Select Export Folder"
 msgstr "选择输出文件夹"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:296
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:297
 msgid ""
 "OpenAI API returned invalid response. Please check the API url or your key. "
 "Transcription and translation may still work if the API does not support key "
@@ -534,57 +539,132 @@ msgstr "查看"
 msgid "Timestamps"
 msgstr "时间戳"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:146
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:150
 msgid "Export"
 msgstr "导出"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:160
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:164
 #: buzz/transcriber/transcriber.py:24
 msgid "Translate"
 msgstr "翻译"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:170
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:168
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:174
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:166
 msgid "Resize"
 msgstr "调整大小"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:269
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:187
+msgid "Identify Speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:286
 msgid "API Key Required"
 msgstr "需要API Key"
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:270
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:287
 msgid "Please enter OpenAI API Key in preferences"
 msgstr "请在偏好设置中输入OpenAI API Key"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:150
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:148
 #, fuzzy
 msgid "Resize Options"
 msgstr "调整大小"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:161
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:159
 msgid "Desired subtitle length"
 msgstr "所需字幕长度"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:186
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:184
 msgid "Merge Options"
 msgstr "合并选项"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:197
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:195
 msgid "Merge by gap"
 msgstr "按间隔合并"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:205
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:203
 msgid "Split by punctuation"
 msgstr "按标点符号拆分"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:213
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:211
 msgid "Split by max length"
 msgstr "按最大长度拆分"
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:225
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:223
 msgid "Merge"
 msgstr "合并"
 
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:101
+msgid "1/9 Collecting transcripts"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:115
+msgid "2/9 Loading audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:124
+msgid "3/9 Loading alignment model"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:130
+msgid "4/9 Preparing audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:142
+#, fuzzy
+msgid "5/9 Preparing transcripts"
+msgstr "打开识别结果"
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:160
+msgid "6/9 Converting audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:174
+msgid "7/9 Identifying speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:184
+msgid "8/9 Mapping speakers to transcripts"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:233
+msgid "9/9 Identification done"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:278
+msgid "Step 1: Identify speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:290
+msgid "Identify"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:300
+msgid "Ready to identify speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:302
+msgid "Audio file not found"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:318
+msgid "Step 2: Name speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:333
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:431
+msgid "Play sample"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:348
+msgid "Merge speaker sentences"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:353
+#, fuzzy
+msgid "Save"
+msgstr "保存文件"
+
 #: buzz/widgets/transcription_viewer/export_transcription_menu.py:78
 #, fuzzy
 msgid "Save File"
@@ -691,10 +771,6 @@ msgstr ""
 msgid "Turkish"
 msgstr ""
 
-#: buzz/transcriber/transcriber.py:50
-msgid "Dutch"
-msgstr ""
-
 #: buzz/transcriber/transcriber.py:51
 msgid "Arabic"
 msgstr ""

buzz/locale/zh_TW/LC_MESSAGES/buzz.po

@@ -7,7 +7,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: \n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2025-03-06 19:12+0200\n"
+"POT-Creation-Date: 2025-04-06 20:58+0300\n"
 "PO-Revision-Date: 2023-05-01 15:45+0800\n"
 "Last-Translator: \n"
 "Language-Team: Lamb\n"
@@ -73,122 +73,127 @@ msgid "Danish"
 msgstr ""
 
 #: buzz/widgets/preferences_dialog/general_preferences_widget.py:38
+#: buzz/transcriber/transcriber.py:50
+msgid "Dutch"
+msgstr ""
+
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:39
 #: buzz/transcriber/transcriber.py:40
 msgid "German"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:39
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:40
 #: buzz/transcriber/transcriber.py:41
 msgid "Spanish"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:40
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:41
 #: buzz/transcriber/transcriber.py:53
 msgid "Italian"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:41
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:42
 #: buzz/transcriber/transcriber.py:45
 msgid "Japanese"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:42
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:43
 #: buzz/transcriber/transcriber.py:80
 msgid "Latvian"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:43
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:44
 #: buzz/transcriber/transcriber.py:48
 msgid "Polish"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:44
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:45
 #: buzz/transcriber/transcriber.py:59
 msgid "Ukrainian"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:45
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:46
 msgid "Chinese (Simplified)"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:46
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:47
 msgid "Chinese (Traditional)"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:84
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:85
 msgid "Restart required!"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:88
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:89
 #, fuzzy
 msgid "Ui Language"
 msgstr "語言:"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:96
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:97
 msgid "Font Size"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:105
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:106
 msgid "Test"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:111
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:112
 msgid "OpenAI API key"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:124
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:125
 msgid "OpenAI base url"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:133
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:134
 msgid "Default export file name"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:139
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:140
 msgid "Enable live recording transcription export"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:145
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:146
 #: buzz/widgets/preferences_dialog/folder_watch_preferences_widget.py:47
 #: buzz/widgets/preferences_dialog/folder_watch_preferences_widget.py:50
 msgid "Browse"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:164
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:165
 msgid "Export folder"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:175
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:176
 #, fuzzy
 msgid "Live recording mode"
 msgstr "現場錄製"
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:200
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:206
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:201
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:207
 msgid "OpenAI API Key Test"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:201
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:202
 msgid ""
 "Your API key is valid. Buzz will use this key to perform Whisper API "
 "transcriptions and AI translations."
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:217
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:218
 msgid "Invalid API key"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:218
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:219
 msgid ""
 "API supports only base64 characters (A-Za-z0-9+/=_-). Other characters in "
 "API key may cause errors."
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:236
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:237
 msgid "Select Export Folder"
 msgstr ""
 
-#: buzz/widgets/preferences_dialog/general_preferences_widget.py:296
+#: buzz/widgets/preferences_dialog/general_preferences_widget.py:297
 msgid ""
 "OpenAI API returned invalid response. Please check the API url or your key. "
 "Transcription and translation may still work if the API does not support key "
@@ -529,56 +534,131 @@ msgstr ""
 msgid "Timestamps"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:146
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:150
 msgid "Export"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:160
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:164
 #: buzz/transcriber/transcriber.py:24
 msgid "Translate"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:170
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:168
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:174
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:166
 msgid "Resize"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:269
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:187
+msgid "Identify Speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:286
 msgid "API Key Required"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:270
+#: buzz/widgets/transcription_viewer/transcription_viewer_widget.py:287
 msgid "Please enter OpenAI API Key in preferences"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:150
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:148
 msgid "Resize Options"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:161
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:159
 msgid "Desired subtitle length"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:186
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:184
 msgid "Merge Options"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:197
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:195
 msgid "Merge by gap"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:205
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:203
 msgid "Split by punctuation"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:213
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:211
 msgid "Split by max length"
 msgstr ""
 
-#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:225
+#: buzz/widgets/transcription_viewer/transcription_resizer_widget.py:223
 msgid "Merge"
 msgstr ""
 
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:101
+msgid "1/9 Collecting transcripts"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:115
+msgid "2/9 Loading audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:124
+msgid "3/9 Loading alignment model"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:130
+msgid "4/9 Preparing audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:142
+#, fuzzy
+msgid "5/9 Preparing transcripts"
+msgstr "打開轉換結果"
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:160
+msgid "6/9 Converting audio"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:174
+msgid "7/9 Identifying speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:184
+msgid "8/9 Mapping speakers to transcripts"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:233
+msgid "9/9 Identification done"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:278
+msgid "Step 1: Identify speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:290
+msgid "Identify"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:300
+msgid "Ready to identify speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:302
+msgid "Audio file not found"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:318
+msgid "Step 2: Name speakers"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:333
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:431
+msgid "Play sample"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:348
+msgid "Merge speaker sentences"
+msgstr ""
+
+#: buzz/widgets/transcription_viewer/speaker_identification_widget.py:353
+#, fuzzy
+msgid "Save"
+msgstr "檔案"
+
 #: buzz/widgets/transcription_viewer/export_transcription_menu.py:78
 #, fuzzy
 msgid "Save File"
@@ -685,10 +765,6 @@ msgstr ""
 msgid "Turkish"
 msgstr ""
 
-#: buzz/transcriber/transcriber.py:50
-msgid "Dutch"
-msgstr ""
-
 #: buzz/transcriber/transcriber.py:51
 msgid "Arabic"
 msgstr ""

buzz/widgets/transcription_viewer/speaker_identification_widget.py

@@ -1,11 +1,14 @@
 import re
 import os
 import logging
-import stable_whisper
-import srt
-from pathlib import Path
+import faster_whisper
+import torch
+import torchaudio
+import random
 from typing import Optional
-from PyQt6.QtCore import Qt, QThread, QObject, pyqtSignal
+from platformdirs import user_cache_dir
+from PyQt6.QtMultimedia import QMediaPlayer, QAudioOutput
+from PyQt6.QtCore import Qt, QThread, QObject, pyqtSignal, QUrl, QTimer
 from PyQt6.QtGui import QFont
 from PyQt6.QtWidgets import (
     QWidget,
@@ -13,14 +16,15 @@ from PyQt6.QtWidgets import (
     QVBoxLayout,
     QHBoxLayout,
     QLabel,
-    QSpinBox,
+    QProgressBar,
     QPushButton,
     QCheckBox,
     QGroupBox,
     QSpacerItem,
     QSizePolicy,
+    QLayout,
 )
-from buzz.locale import _, languages
+from buzz.locale import _
 from buzz.db.entity.transcription import Transcription
 from buzz.db.service.transcription_service import TranscriptionService
 from buzz.paths import file_path_as_title
@@ -31,19 +35,38 @@ from buzz.widgets.preferences_dialog.models.file_transcription_preferences impor
     FileTranscriptionPreferences,
 )
 
+from ctc_forced_aligner import (
+    generate_emissions,
+    get_alignments,
+    get_spans,
+    load_alignment_model,
+    postprocess_results,
+    preprocess_text,
+)
+from whisper_diarization.helpers import (
+    cleanup,
+    create_config,
+    get_realigned_ws_mapping_with_punctuation,
+    get_sentences_speaker_mapping,
+    get_words_speaker_mapping,
+    langs_to_iso,
+    punct_model_langs,
+)
+from deepmultilingualpunctuation import PunctuationModel
+from nemo.collections.asr.models.msdd_models import NeuralDiarizer
+
 
 SENTENCE_END = re.compile(r'.*[.!?。！？]')
 
-class TranscriptionWorker(QObject):
-    finished = pyqtSignal()
-    result_ready = pyqtSignal(list)
+class IdentificationWorker(QObject):
+    finished = pyqtSignal(list)
+    progress_update = pyqtSignal(str)
 
-    def __init__(self, transcription, transcription_options, transcription_service, regroup_string: str):
+    def __init__(self, transcription, transcription_options, transcription_service):
         super().__init__()
         self.transcription = transcription
         self.transcription_options = transcription_options
         self.transcription_service = transcription_service
-        self.regroup_string = regroup_string
 
     def get_transcript(self, audio, **kwargs) -> dict:
         buzz_segments = self.transcription_service.get_transcription_segments(
@@ -75,36 +98,139 @@ class TranscriptionWorker(QObject):
         }
 
     def run(self):
-        transcription_file = self.transcription.file
-        transcription_file_exists = os.path.exists(transcription_file)
+        self.progress_update.emit(_("1/9 Collecting transcripts"))
 
-        transcription_file_path = Path(transcription_file)
-        speech_path = transcription_file_path.with_name(f"{transcription_file_path.stem}_speech.mp3")
-        if self.transcription_options.extract_speech and os.path.exists(speech_path):
-            transcription_file = str(speech_path)
-            transcription_file_exists = True
+        # Step 1 - Get transcript
+        # TODO - Add detected language to the transcript, detect and store separately in metadata
+        #        Will also be relevant for template parsing of transcript file names
+        #        - See diarize.py for example on how to get this info from whisper transcript, maybe other whisper models also have it
+        language = self.transcription.language if self.transcription.language else "en"
 
-        result = stable_whisper.transcribe_any(
-            self.get_transcript,
-            transcription_file,
-            vad=transcription_file_exists,
-            suppress_silence=transcription_file_exists,
-            regroup=self.regroup_string,
-            check_sorted=False,
+        segments = self.transcription_service.get_transcription_segments(
+            transcription_id=self.transcription.id_as_uuid
         )
 
-        segments = []
-        for segment in result.segments:
-            segments.append(
-                Segment(
-                    start=int(segment.start * 100),
-                    end=int(segment.end * 100),
-                    text=segment.text
-                )
+        full_transcript = "".join(segment.text for segment in segments)
+
+        self.progress_update.emit(_("2/9 Loading audio"))
+        audio_waveform = faster_whisper.decode_audio(self.transcription.file)
+
+        # Step 2 - Forced alignment
+        force_cpu = os.getenv("BUZZ_FORCE_CPU", "false")
+        use_cuda = torch.cuda.is_available() and force_cpu == "false"
+        device = "cuda" if use_cuda else "cpu"
+        torch_dtype = torch.float16 if use_cuda else torch.float32
+
+        self.progress_update.emit(_("3/9 Loading alignment model"))
+        alignment_model, alignment_tokenizer = load_alignment_model(
+            device,
+            dtype=torch_dtype,
+        )
+
+        self.progress_update.emit(_("4/9 Preparing audio"))
+        emissions, stride = generate_emissions(
+            alignment_model,
+            torch.from_numpy(audio_waveform)
+            .to(alignment_model.dtype)
+            .to(alignment_model.device),
+            batch_size=8,
+        )
+
+        del alignment_model
+        torch.cuda.empty_cache()
+
+        self.progress_update.emit(_("5/9 Preparing transcripts"))
+        tokens_starred, text_starred = preprocess_text(
+            full_transcript,
+            romanize=True,
+            language=langs_to_iso[language],
+        )
+
+        segments, scores, blank_token = get_alignments(
+            emissions,
+            tokens_starred,
+            alignment_tokenizer,
+        )
+
+        spans = get_spans(tokens_starred, segments, blank_token)
+
+        word_timestamps = postprocess_results(text_starred, spans, stride, scores)
+
+        # convert audio to mono for NeMo compatibility
+        self.progress_update.emit(_("6/9 Converting audio"))
+        model_root_dir = user_cache_dir("Buzz")
+        model_root_dir = os.getenv("BUZZ_MODEL_ROOT", model_root_dir)
+        temp_path = os.path.join(model_root_dir, "speaker_identification_temp")
+        os.makedirs(temp_path, exist_ok=True)
+        torchaudio.save(
+            os.path.join(temp_path, "mono_file.wav"),
+            torch.from_numpy(audio_waveform).unsqueeze(0).float(),
+            16000,
+            channels_first=True,
+        )
+
+        # Step 3 - Diarization
+        self.progress_update.emit(_("7/9 Identifying speakers"))
+        logging.basicConfig(level=logging.INFO)
+        logging.getLogger("nemo_logger").setLevel(logging.ERROR)
+        msdd_model = NeuralDiarizer(cfg=create_config(temp_path)).to(device)
+        msdd_model.diarize()
+
+        del msdd_model
+        torch.cuda.empty_cache()
+
+        # Step 4 - Reading timestamps <> Speaker Labels mapping
+        self.progress_update.emit(_("8/9 Mapping speakers to transcripts"))
+        speaker_ts = []
+        with open(os.path.join(temp_path, "pred_rttms", "mono_file.rttm"), "r") as f:
+            lines = f.readlines()
+            for line in lines:
+                line_list = line.split(" ")
+                s = int(float(line_list[5]) * 1000)
+                e = s + int(float(line_list[8]) * 1000)
+                speaker_ts.append([s, e, int(line_list[11].split("_")[-1])])
+
+        wsm = get_words_speaker_mapping(word_timestamps, speaker_ts, "start")
+
+        if language in punct_model_langs:
+            # restoring punctuation in the transcript to help realign the sentences
+            punct_model = PunctuationModel(model="kredor/punctuate-all")
+
+            words_list = list(map(lambda x: x["word"], wsm))
+
+            labled_words = punct_model.predict(words_list, chunk_size=230)
+
+            ending_puncts = ".?!。！？"
+            model_puncts = ".,;:!?。！？"
+
+            # We don't want to punctuate U.S.A. with a period. Right?
+            is_acronym = lambda x: re.fullmatch(r"\b(?:[a-zA-Z]\.){2,}", x)
+
+            for word_dict, labeled_tuple in zip(wsm, labled_words):
+                word = word_dict["word"]
+                if (
+                        word
+                        and labeled_tuple[1] in ending_puncts
+                        and (word[-1] not in model_puncts or is_acronym(word))
+                ):
+                    word += labeled_tuple[1]
+                    if word.endswith(".."):
+                        word = word.rstrip(".")
+                    word_dict["word"] = word
+
+        else:
+            logging.warning(
+                f"Punctuation restoration is not available for {language} language."
+                " Using the original punctuation."
             )
 
-        self.result_ready.emit(segments)
-        self.finished.emit()
+        wsm = get_realigned_ws_mapping_with_punctuation(wsm)
+        ssm = get_sentences_speaker_mapping(wsm, speaker_ts)
+
+        cleanup(temp_path)
+
+        self.progress_update.emit(_("9/9 Identification done"))
+        self.finished.emit(ssm)
 
 
 class SpeakerIdentificationWidget(QWidget):
@@ -125,12 +251,13 @@ class SpeakerIdentificationWidget(QWidget):
         self.transcription_service = transcription_service
         self.transcriptions_updated_signal = transcriptions_updated_signal
 
-        self.new_transcript_id = None
+        self.identification_result = None
+
         self.thread = None
         self.worker = None
 
-        self.setMinimumWidth(600)
-        self.setMinimumHeight(300)
+        self.setMinimumWidth(650)
+        self.setMinimumHeight(400)
 
         self.setWindowTitle(file_path_as_title(transcription.file))
 
@@ -144,182 +271,262 @@ class SpeakerIdentificationWidget(QWidget):
         )
 
         layout = QFormLayout(self)
+        layout.setSizeConstraint(QLayout.SizeConstraint.SetMinAndMaxSize)
 
-        # Resize longer subtitles
-        resize_label = QLabel(_("Resize Options"), self)
-        font = resize_label.font()
+        # Step 1: Identify speakers
+        step_1_label = QLabel(_("Step 1: Identify speakers"), self)
+        font = step_1_label.font()
         font.setWeight(QFont.Weight.Bold)
-        resize_label.setFont(font)
-        layout.addRow(resize_label)
+        step_1_label.setFont(font)
+        layout.addRow(step_1_label)
 
-        resize_group_box = QGroupBox(self)
-        resize_layout = QVBoxLayout(resize_group_box)
+        step_1_group_box = QGroupBox(self)
+        step_1_group_box.setSizePolicy(QSizePolicy.Policy.Expanding, QSizePolicy.Policy.Expanding)
+        step_1_layout = QVBoxLayout(step_1_group_box)
 
-        self.resize_row = QHBoxLayout()
+        self.step_1_row = QHBoxLayout()
 
-        self.desired_subtitle_length_label = QLabel(_("Desired subtitle length"), self)
+        self.step_1_button = QPushButton(_("Identify"))
+        self.step_1_button.setMinimumWidth(200)
+        self.step_1_button.clicked.connect(self.on_identify_button_clicked)
 
-        self.target_chars_spin_box = QSpinBox(self)
-        self.target_chars_spin_box.setMinimum(1)
-        self.target_chars_spin_box.setMaximum(100)
-        self.target_chars_spin_box.setValue(42)
+        self.progress_bar = QProgressBar(self)
+        self.progress_bar.setMinimumWidth(400)
+        self.progress_bar.setRange(0, 9)
+        self.progress_bar.setValue(0)
 
-        self.resize_button = QPushButton(_("Resize"))
-        self.resize_button.clicked.connect(self.on_resize_button_clicked)
+        if os.path.isfile(self.transcription.file):
+            self.progress_bar.setFormat(_("Ready to identify speakers"))
+        else:
+            self.progress_bar.setFormat(_("Audio file not found"))
+            self.step_1_button.setEnabled(False)
 
-        self.resize_row.addWidget(self.desired_subtitle_length_label)
-        self.resize_row.addWidget(self.target_chars_spin_box)
-        self.resize_row.addWidget(self.resize_button)
+        self.step_1_row.addWidget(self.progress_bar)
 
-        resize_layout.addLayout(self.resize_row)
+        self.step_1_row.addWidget(self.step_1_button)
 
-        resize_group_box.setEnabled(self.transcription.word_level_timings != 1)
+        step_1_layout.addLayout(self.step_1_row)
 
-        layout.addRow(resize_group_box)
+        layout.addRow(step_1_group_box)
 
         # Spacer
         spacer = QSpacerItem(0, 10, QSizePolicy.Policy.Minimum, QSizePolicy.Policy.Fixed)
         layout.addItem(spacer)
 
-        # Merge words into subtitles
-        merge_options_label = QLabel(_("Merge Options"), self)
-        font = merge_options_label.font()
+        # Step 2: Name speakers
+        step_2_label = QLabel(_("Step 2: Name speakers"), self)
+        font = step_2_label.font()
         font.setWeight(QFont.Weight.Bold)
-        merge_options_label.setFont(font)
-        layout.addRow(merge_options_label)
+        step_2_label.setFont(font)
+        layout.addRow(step_2_label)
 
-        merge_options_group_box = QGroupBox(self)
-        merge_options_layout = QVBoxLayout(merge_options_group_box)
+        self.step_2_group_box = QGroupBox(self)
+        self.step_2_group_box.setSizePolicy(QSizePolicy.Policy.Expanding, QSizePolicy.Policy.Expanding)
+        self.step_2_group_box.setEnabled(False)
+        step_2_layout = QVBoxLayout(self.step_2_group_box)
 
-        self.merge_options_row = QVBoxLayout()
+        self.speaker_preview_row = QVBoxLayout()
 
-        self.merge_by_gap = QCheckBox(_("Merge by gap"))
-        self.merge_by_gap.setChecked(True)
-        self.merge_by_gap.setMinimumWidth(250)
-        self.merge_by_gap_input = LineEdit("0.2", self)
-        merge_by_gap_layout = QHBoxLayout()
-        merge_by_gap_layout.addWidget(self.merge_by_gap)
-        merge_by_gap_layout.addWidget(self.merge_by_gap_input)
+        self.speaker_0_input = LineEdit("Speaker 0", self)
 
-        self.split_by_punctuation = QCheckBox(_("Split by punctuation"))
-        self.split_by_punctuation.setChecked(True)
-        self.split_by_punctuation.setMinimumWidth(250)
-        self.split_by_punctuation_input = LineEdit(".* /./. /。/?/? /？/!/! /！/,/, ", self)
-        split_by_punctuation_layout = QHBoxLayout()
-        split_by_punctuation_layout.addWidget(self.split_by_punctuation)
-        split_by_punctuation_layout.addWidget(self.split_by_punctuation_input)
+        self.speaker_0_preview_button = QPushButton(_("Play sample"))
+        self.speaker_0_preview_button.setMinimumWidth(200)
+        self.speaker_0_preview_button.clicked.connect(lambda: self.on_speaker_preview("Speaker 0"))
 
-        self.split_by_max_length = QCheckBox(_("Split by max length"))
-        self.split_by_max_length.setChecked(True)
-        self.split_by_max_length.setMinimumWidth(250)
-        self.split_by_max_length_input = LineEdit("42", self)
-        split_by_max_length_layout = QHBoxLayout()
-        split_by_max_length_layout.addWidget(self.split_by_max_length)
-        split_by_max_length_layout.addWidget(self.split_by_max_length_input)
+        speaker_0_layout = QHBoxLayout()
+        speaker_0_layout.addWidget(self.speaker_0_input)
+        speaker_0_layout.addWidget(self.speaker_0_preview_button)
 
-        self.merge_options_row.addLayout(merge_by_gap_layout)
-        self.merge_options_row.addLayout(split_by_punctuation_layout)
-        self.merge_options_row.addLayout(split_by_max_length_layout)
+        self.speaker_preview_row.addLayout(speaker_0_layout)
 
-        self.merge_button = QPushButton(_("Merge"))
-        self.merge_button.clicked.connect(self.on_merge_button_clicked)
+        step_2_layout.addLayout(self.speaker_preview_row)
 
-        self.merge_options_row.addWidget(self.merge_button)
+        layout.addRow(self.step_2_group_box)
 
-        merge_options_layout.addLayout(self.merge_options_row)
+        # Save button
+        self.merge_speaker_sentences = QCheckBox(_("Merge speaker sentences"))
+        self.merge_speaker_sentences.setChecked(True)
+        self.merge_speaker_sentences.setEnabled(False)
+        self.merge_speaker_sentences.setMinimumWidth(250)
 
-        merge_options_group_box.setEnabled(self.transcription.word_level_timings == 1)
+        self.save_button = QPushButton(_("Save"))
+        self.save_button.setEnabled(False)
+        self.save_button.clicked.connect(self.on_save_button_clicked)
 
-        layout.addRow(merge_options_group_box)
+        layout.addRow(self.merge_speaker_sentences)
+        layout.addRow(self.save_button)
 
         self.setLayout(layout)
 
+        # Invisible preview player
+        url = QUrl.fromLocalFile(self.transcription.file)
+        self.player = QMediaPlayer()
+        self.audio_output = QAudioOutput()
+        self.player.setAudioOutput(self.audio_output)
+        self.player.setSource(url)
+        self.player_timer = None
+
     def load_preferences(self):
         self.settings.settings.beginGroup("file_transcriber")
         preferences = FileTranscriptionPreferences.load(settings=self.settings.settings)
         self.settings.settings.endGroup()
         return preferences
 
-    # TODO rename function
-    def on_resize_button_clicked(self):
-        #  Step 1 - Get the segments
-        segments = self.transcription_service.get_transcription_segments(
-            transcription_id=self.transcription.id_as_uuid
-        )
-
-        subs = []
-        for segment in segments:
-            subtitle = srt.Subtitle(
-                index=segment.id,
-                start=segment.start_time,
-                end=segment.end_time,
-                content=segment.text
-            )
-            subs.append(subtitle)
-
-        # Step 2 - ...
-        logging.debug(f"=== Will identify speakers ===")
-
-    def on_merge_button_clicked(self):
-        self.new_transcript_id = self.transcription_service.copy_transcription(
-            self.transcription.id_as_uuid
-        )
-        self.transcription_service.update_transcription_progress(self.new_transcript_id, 0.0)
-
-        if self.transcriptions_updated_signal:
-            self.transcriptions_updated_signal.emit(self.new_transcript_id)
-
-        regroup_string = ''
-        if self.merge_by_gap.isChecked():
-            regroup_string += f'mg={self.merge_by_gap_input.text()}'
-
-            if self.split_by_max_length.isChecked():
-                regroup_string += f'++{self.split_by_max_length_input.text()}+1'
-
-        if self.split_by_punctuation.isChecked():
-            if regroup_string:
-                regroup_string += '_'
-            regroup_string += f'sp={self.split_by_punctuation_input.text()}'
-
-        if self.split_by_max_length.isChecked():
-            if regroup_string:
-                regroup_string += '_'
-            regroup_string += f'sl={self.split_by_max_length_input.text()}'
-
-        if self.merge_by_gap.isChecked():
-            if regroup_string:
-                regroup_string += '_'
-            regroup_string += f'mg={self.merge_by_gap_input.text()}'
-
-            if self.split_by_max_length.isChecked():
-                regroup_string += f'++{self.split_by_max_length_input.text()}+1'
-
-        regroup_string = os.getenv("BUZZ_MERGE_REGROUP_RULE", regroup_string)
-
-        self.hide()
-
+    def on_identify_button_clicked(self):
         self.thread = QThread()
-        self.worker = TranscriptionWorker(
+        self.worker = IdentificationWorker(
             self.transcription,
             self.transcription_options,
-            self.transcription_service,
-            regroup_string
+            self.transcription_service
         )
         self.worker.moveToThread(self.thread)
         self.thread.started.connect(self.worker.run)
         self.worker.finished.connect(self.thread.quit)
         self.worker.finished.connect(self.worker.deleteLater)
         self.thread.finished.connect(self.thread.deleteLater)
-        self.worker.result_ready.connect(self.on_transcription_completed)
+        self.worker.finished.connect(self.on_identification_finished)
+        self.worker.progress_update.connect(self.on_progress_update)
 
         self.thread.start()
 
-    def on_transcription_completed(self, segments):
-        if self.new_transcript_id is not None:
-            self.transcription_service.update_transcription_as_completed(self.new_transcript_id, segments)
+    def on_progress_update(self, progress):
+        self.progress_bar.setFormat(progress)
 
-            if self.transcriptions_updated_signal:
-                self.transcriptions_updated_signal.emit(self.new_transcript_id)
+        progress_value = 0
+        if progress and progress[0].isdigit():
+            progress_value = int(progress[0])
+            self.progress_bar.setValue(progress_value)
+        else:
+            logging.error(f"Invalid progress format: {progress}")
+
+        if progress_value == 9:
+            self.step_2_group_box.setEnabled(True)
+            self.merge_speaker_sentences.setEnabled(True)
+            self.save_button.setEnabled(True)
+
+    def on_identification_finished(self, result):
+        self.identification_result = result
+
+        unique_speakers = {entry['speaker'] for entry in result}
+
+        while self.speaker_preview_row.count():
+            item = self.speaker_preview_row.takeAt(0)
+            widget = item.widget()
+            if widget:
+                widget.deleteLater()
+            else:
+                layout = item.layout()
+                if layout:
+                    while layout.count():
+                        sub_item = layout.takeAt(0)
+                        sub_widget = sub_item.widget()
+                        if sub_widget:
+                            sub_widget.deleteLater()
+
+        for speaker in sorted(unique_speakers):
+            speaker_input = LineEdit(speaker, self)
+            speaker_input.setMinimumWidth(200)
+
+            speaker_preview_button = QPushButton(_("Play sample"))
+            speaker_preview_button.setMinimumWidth(200)
+            speaker_preview_button.clicked.connect(lambda checked, s=speaker: self.on_speaker_preview(s))
+
+            speaker_layout = QHBoxLayout()
+            speaker_layout.addWidget(speaker_input)
+            speaker_layout.addWidget(speaker_preview_button)
+
+            self.speaker_preview_row.addLayout(speaker_layout)
+
+    def on_speaker_preview(self, speaker_id):
+        if self.player_timer:
+            self.player_timer.stop()
+
+        speaker_records = [record for record in self.identification_result if record['speaker'] == speaker_id]
+
+        if speaker_records:
+            random_record = random.choice(speaker_records)
+
+            start_time = random_record['start_time']
+            end_time = random_record['end_time']
+
+            self.player.setPosition(int(start_time))
+            self.player.play()
+
+            self.player_timer = QTimer(self)
+            self.player_timer.setSingleShot(True)
+            self.player_timer.timeout.connect(self.player.stop)
+            self.player_timer.start(min(end_time, 10 * 1000))  # 10 seconds
+
+    def on_save_button_clicked(self):
+        speaker_names = []
+        for i in range(self.speaker_preview_row.count()):
+            item = self.speaker_preview_row.itemAt(i)
+            if item.layout():
+                for j in range(item.layout().count()):
+                    sub_item = item.layout().itemAt(j)
+                    widget = sub_item.widget()
+                    if isinstance(widget, LineEdit):
+                        speaker_names.append(widget.text())
+
+        unique_speakers = {entry['speaker'] for entry in self.identification_result}
+        original_speakers = sorted(unique_speakers)
+        speaker_mapping = dict(zip(original_speakers, speaker_names))
+
+        segments = []
+        if self.merge_speaker_sentences.isChecked():
+            previous_segment = None
+
+            for entry in self.identification_result:
+                speaker_name = speaker_mapping.get(entry['speaker'], entry['speaker'])
+
+                if previous_segment and previous_segment['speaker'] == speaker_name:
+                    previous_segment['end_time'] = entry['end_time']
+                    previous_segment['text'] += " " + entry['text']
+                else:
+                    if previous_segment:
+                        segment = Segment(
+                            start=previous_segment['start_time'],
+                            end=previous_segment['end_time'],
+                            text=f"{previous_segment['speaker']}: {previous_segment['text']}"
+                        )
+                        segments.append(segment)
+                    previous_segment = {
+                        'start_time': entry['start_time'],
+                        'end_time': entry['end_time'],
+                        'speaker': speaker_name,
+                        'text': entry['text']
+                    }
+
+            if previous_segment:
+                segment = Segment(
+                    start=previous_segment['start_time'],
+                    end=previous_segment['end_time'],
+                    text=f"{previous_segment['speaker']}: {previous_segment['text']}"
+                )
+                segments.append(segment)
+        else:
+            for entry in self.identification_result:
+                speaker_name = speaker_mapping.get(entry['speaker'], entry['speaker'])
+                segment = Segment(
+                    start=entry['start_time'],
+                    end=entry['end_time'],
+                    text=f"{speaker_name}: {entry['text']}"
+                )
+                segments.append(segment)
+
+        new_transcript_id = self.transcription_service.copy_transcription(
+            self.transcription.id_as_uuid
+        )
+
+        self.transcription_service.update_transcription_as_completed(new_transcript_id, segments)
+
+        if self.transcriptions_updated_signal:
+            self.transcriptions_updated_signal.emit(new_transcript_id)
+
+        self.player.stop()
+
+        if self.player_timer:
+            self.player_timer.stop()
 
         self.close()
 

buzz/widgets/transcription_viewer/transcription_resizer_widget.py

@@ -36,8 +36,7 @@ from buzz.widgets.preferences_dialog.models.file_transcription_preferences impor
 SENTENCE_END = re.compile(r'.*[.!?。！？]')
 
 class TranscriptionWorker(QObject):
-    finished = pyqtSignal()
-    result_ready = pyqtSignal(list)
+    finished = pyqtSignal(list)
 
     def __init__(self, transcription, transcription_options, transcription_service, regroup_string: str):
         super().__init__()
@@ -104,8 +103,7 @@ class TranscriptionWorker(QObject):
                 )
             )
 
-        self.result_ready.emit(segments)
-        self.finished.emit()
+        self.finished.emit(segments)
 
 
 class TranscriptionResizerWidget(QWidget):
@@ -335,7 +333,7 @@ class TranscriptionResizerWidget(QWidget):
         self.worker.finished.connect(self.thread.quit)
         self.worker.finished.connect(self.worker.deleteLater)
         self.thread.finished.connect(self.thread.deleteLater)
-        self.worker.result_ready.connect(self.on_transcription_completed)
+        self.worker.finished.connect(self.on_transcription_completed)
 
         self.thread.start()
 

buzz/widgets/transcription_viewer/transcription_viewer_widget.py

@@ -1,4 +1,5 @@
 import logging
+import platform
 from typing import Optional
 from uuid import UUID
 
@@ -194,16 +195,18 @@ class TranscriptionViewerWidget(QWidget):
 
         toolbar.addWidget(resize_button)
 
-        speaker_identification_button = QToolButton()
-        speaker_identification_button.setText(_("Identify Speakers"))
-        speaker_identification_button.setObjectName("speaker_identification_button")
-        speaker_identification_button.setIcon(SpeakerIdentificationIcon(self))
-        speaker_identification_button.setToolButtonStyle(
-            Qt.ToolButtonStyle.ToolButtonTextBesideIcon
-        )
-        speaker_identification_button.clicked.connect(self.on_speaker_identification_button_clicked)
+        # Underlying libs do not support intel Macs
+        if not (platform.system() == "Darwin" and platform.machine() == "x86_64"):
+            speaker_identification_button = QToolButton()
+            speaker_identification_button.setText(_("Identify Speakers"))
+            speaker_identification_button.setObjectName("speaker_identification_button")
+            speaker_identification_button.setIcon(SpeakerIdentificationIcon(self))
+            speaker_identification_button.setToolButtonStyle(
+                Qt.ToolButtonStyle.ToolButtonTextBesideIcon
+            )
+            speaker_identification_button.clicked.connect(self.on_speaker_identification_button_clicked)
 
-        toolbar.addWidget(speaker_identification_button)
+            toolbar.addWidget(speaker_identification_button)
 
         layout.setMenuBar(toolbar)
 

docs/docs/preferences.md

@@ -88,7 +88,7 @@ combined to produce the final answer.
 
 **BUZZ_TRANSLATION_API_KEY** - Api key of OpenAI compatible API to use for translation.
 
-**BUZZ_MODEL_ROOT** - Root directory to store model files.
+**BUZZ_MODEL_ROOT** - Root directory to store model files. You may also want to set `HF_HOME` to the same folder as some libraries used in Buzz download their models independently. 
 Defaults to [user_cache_dir](https://pypi.org/project/platformdirs/).
 
 **BUZZ_FAVORITE_LANGUAGES** - Coma separated list of supported language codes to show on top of language list.

docs/docs/usage/1_file_import.md

@@ -20,3 +20,5 @@ To import a file:
 (See the [Live Recording section](https://chidiwilliams.github.io/buzz/docs/usage/live_recording) for more information about the task, language, and quality settings.)
 
 [![Media File Import on Buzz](https://cdn.loom.com/sessions/thumbnails/cf263b099ac3481082bb56d19b7c87fe-with-play.gif)](https://www.loom.com/share/cf263b099ac3481082bb56d19b7c87fe "Media File Import on Buzz")
+
+**💡 Tip:** It is recommended to always select language to transcribe to as automatic language detection may result in unexpected results.

docs/docs/usage/5_speaker_identification.md

@@ -0,0 +1,9 @@
+---
+title: Speaker identification
+---
+
+When transcript of some audio or video file is generated you can identify speakers in the transcript. Double-click the transcript in the list of transcripts to see additional options for editing and exporting.
+
+Transcription view screen has option to identify speakers. Click on the "Identify speakers" button so see available options.  
+
+If audio file is still present on the system speaker identification will mark each speakers sentences with appropriate label. You can preview 10 seconds of some random sentence of the identified speaker and rename the automatically identified label to speakers real name. If "Merge speaker sentences" checkbox is selected when you save the speaker labels, all consecutive sentences of the same speaker wil lbe merged into one segment. Speaker identification is available since version 1.3.0.

poetry.lock

@@ -1275,44 +1275,47 @@ typing-inspect = ">=0.4.0,<1"
 
 [[package]]
 name = "datasets"
-version = "2.2.1"
+version = "3.5.0"
 description = "HuggingFace community-driven open-source library of datasets"
 optional = false
-python-versions = "*"
+python-versions = ">=3.9.0"
 groups = ["main"]
 files = [
-    {file = "datasets-2.2.1-py3-none-any.whl", hash = "sha256:1938f3e99599422de50b9b54fe802aca854ed130382dab0b3820c821f7ae6d5e"},
-    {file = "datasets-2.2.1.tar.gz", hash = "sha256:d362717c4394589b516c8f397ff20a6fe720454aed877ab61d06f3bc05df9544"},
+    {file = "datasets-3.5.0-py3-none-any.whl", hash = "sha256:b3b7f163acc6ac4e01a1b00eef26d48bd4039288ceea3601d169272bd5581006"},
+    {file = "datasets-3.5.0.tar.gz", hash = "sha256:9e39560e34f83a64e48ceca7adeb645ede3c3055c5cf48ed2b454f8ed2b89754"},
 ]
 
 [package.dependencies]
 aiohttp = "*"
-dill = "*"
-fsspec = {version = ">=2021.05.0", extras = ["http"]}
-huggingface-hub = ">=0.1.0,<1.0.0"
-multiprocess = "*"
+dill = ">=0.3.0,<0.3.9"
+filelock = "*"
+fsspec = {version = ">=2023.1.0,<=2024.12.0", extras = ["http"]}
+huggingface-hub = ">=0.24.0"
+multiprocess = "<0.70.17"
 numpy = ">=1.17"
 packaging = "*"
 pandas = "*"
-pyarrow = ">=6.0.0"
-requests = ">=2.19.0"
-responses = "<0.19"
-tqdm = ">=4.62.1"
+pyarrow = ">=15.0.0"
+pyyaml = ">=5.1"
+requests = ">=2.32.2"
+tqdm = ">=4.66.3"
 xxhash = "*"
 
 [package.extras]
-apache-beam = ["apache-beam (>=2.26.0)"]
-audio = ["librosa"]
-benchmarks = ["numpy (==1.18.5)", "tensorflow (==2.3.0)", "torch (==1.6.0)", "transformers (==3.0.2)"]
-dev = ["Pillow (>=6.2.1)", "Werkzeug (>=1.0.1)", "absl-py", "aiobotocore", "apache-beam (>=2.26.0)", "bert-score (>=0.3.6)", "black (>=22.0,<23.0)", "boto3", "botocore", "bs4", "conllu", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "flake8 (>=3.8.3)", "fsspec[s3]", "h5py", "importlib-resources ; python_version < \"3.7\"", "isort (>=5.0.0)", "jiwer", "langdetect", "librosa", "lxml", "lz4", "mauve-text", "moto[s3,server] (==2.0.4)", "mwparserfromhell", "nltk", "openpyxl", "py7zr", "pytest", "pytest-datadir", "pytest-xdist", "pyyaml (>=5.3.1)", "rarfile (>=4.0)", "requests-file (>=1.5.1)", "rouge-score", "s3fs (==2021.08.1)", "sacrebleu", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "soundfile", "tensorflow (>=2.3,!=2.6.0,!=2.6.1)", "texttable (>=1.6.3)", "tldextract", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "torch", "torchaudio", "transformers", "zstandard"]
-docs = ["s3fs"]
-quality = ["black (>=22.0,<23.0)", "flake8 (>=3.8.3)", "isort (>=5.0.0)", "pyyaml (>=5.3.1)"]
-s3 = ["boto3", "botocore", "fsspec", "s3fs"]
-tensorflow = ["tensorflow (>=2.2.0,!=2.6.0,!=2.6.1)"]
-tensorflow-gpu = ["tensorflow-gpu (>=2.2.0,!=2.6.0,!=2.6.1)"]
-tests = ["Pillow (>=6.2.1)", "Werkzeug (>=1.0.1)", "absl-py", "aiobotocore", "apache-beam (>=2.26.0)", "bert-score (>=0.3.6)", "boto3", "botocore", "bs4", "conllu", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "fsspec[s3]", "h5py", "importlib-resources ; python_version < \"3.7\"", "jiwer", "langdetect", "librosa", "lxml", "lz4", "mauve-text", "moto[s3,server] (==2.0.4)", "mwparserfromhell", "nltk", "openpyxl", "py7zr", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "requests-file (>=1.5.1)", "rouge-score", "s3fs (==2021.08.1)", "sacrebleu", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "soundfile", "tensorflow (>=2.3,!=2.6.0,!=2.6.1)", "texttable (>=1.6.3)", "tldextract", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "torch", "torchaudio", "transformers", "zstandard"]
+audio = ["librosa", "soundfile (>=0.12.1)", "soxr (>=0.4.0) ; python_version >= \"3.9\""]
+benchmarks = ["tensorflow (==2.12.0)", "torch (==2.0.1)", "transformers (==4.30.1)"]
+dev = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (>=7.17.12,<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14) ; sys_platform != \"win32\"", "jaxlib (>=0.3.14) ; sys_platform != \"win32\"", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyav", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0) ; python_version >= \"3.9\"", "sqlalchemy", "tensorflow (>=2.16.0) ; python_version >= \"3.10\"", "tensorflow (>=2.6.0)", "tensorflow (>=2.6.0) ; python_version < \"3.10\"", "tiktoken", "torch", "torch (>=2.0.0)", "torchdata", "torchvision", "transformers", "transformers (>=4.42.0)", "zstandard"]
+docs = ["s3fs", "tensorflow (>=2.6.0)", "torch", "transformers"]
+jax = ["jax (>=0.3.14)", "jaxlib (>=0.3.14)"]
+pdfs = ["pdfplumber (>=0.11.4)"]
+quality = ["ruff (>=0.3.0)"]
+s3 = ["s3fs"]
+tensorflow = ["tensorflow (>=2.6.0)"]
+tensorflow-gpu = ["tensorflow (>=2.6.0)"]
+tests = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (>=7.17.12,<8.0.0)", "faiss-cpu (>=1.8.0.post1)", "jax (>=0.3.14) ; sys_platform != \"win32\"", "jaxlib (>=0.3.14) ; sys_platform != \"win32\"", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyav", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0) ; python_version >= \"3.9\"", "sqlalchemy", "tensorflow (>=2.16.0) ; python_version >= \"3.10\"", "tensorflow (>=2.6.0) ; python_version < \"3.10\"", "tiktoken", "torch (>=2.0.0)", "torchdata", "torchvision", "transformers (>=4.42.0)", "zstandard"]
+tests-numpy2 = ["Pillow (>=9.4.0)", "absl-py", "decorator", "elasticsearch (>=7.17.12,<8.0.0)", "jax (>=0.3.14) ; sys_platform != \"win32\"", "jaxlib (>=0.3.14) ; sys_platform != \"win32\"", "joblib (<1.3.0)", "joblibspark", "lz4", "moto[server]", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyav", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "soundfile (>=0.12.1)", "soxr (>=0.4.0) ; python_version >= \"3.9\"", "sqlalchemy", "tiktoken", "torch (>=2.0.0)", "torchdata", "torchvision", "transformers (>=4.42.0)", "zstandard"]
 torch = ["torch"]
-vision = ["Pillow (>=6.2.1)"]
+vision = ["Pillow (>=9.4.0)"]
 
 [[package]]
 name = "decorator"
@@ -1422,14 +1425,14 @@ dev = ["coverage", "flake8", "pdoc3", "torchvision"]
 
 [[package]]
 name = "dill"
-version = "0.3.9"
+version = "0.3.8"
 description = "serialize all of Python"
 optional = false
 python-versions = ">=3.8"
 groups = ["main", "dev"]
 files = [
-    {file = "dill-0.3.9-py3-none-any.whl", hash = "sha256:468dff3b89520b474c0397703366b7b95eebe6303f108adf9b19da1f702be87a"},
-    {file = "dill-0.3.9.tar.gz", hash = "sha256:81aa267dddf68cbfe8029c42ca9ec6a4ab3b22371d1c450abc54422577b4512c"},
+    {file = "dill-0.3.8-py3-none-any.whl", hash = "sha256:c36ca9ffb54365bdd2f8eb3eff7d2a21237f8452b57ace88b1ac615b7e815bd7"},
+    {file = "dill-0.3.8.tar.gz", hash = "sha256:3ebe3c479ad625c4553aca177444d89b486b1d84982eeacded644afc0cf797ca"},
 ]
 
 [package.extras]
@@ -1930,14 +1933,14 @@ files = [
 
 [[package]]
 name = "fsspec"
-version = "2025.3.0"
+version = "2024.12.0"
 description = "File-system specification"
 optional = false
 python-versions = ">=3.8"
 groups = ["main"]
 files = [
-    {file = "fsspec-2025.3.0-py3-none-any.whl", hash = "sha256:efb87af3efa9103f94ca91a7f8cb7a4df91af9f74fc106c9c7ea0efd7277c1b3"},
-    {file = "fsspec-2025.3.0.tar.gz", hash = "sha256:a935fd1ea872591f2b5148907d103488fc523295e6c64b835cfad8c3eca44972"},
+    {file = "fsspec-2024.12.0-py3-none-any.whl", hash = "sha256:b520aed47ad9804237ff878b504267a3b0b441e97508bd6d2d8774e3db85cee2"},
+    {file = "fsspec-2024.12.0.tar.gz", hash = "sha256:670700c977ed2fb51e0d9f9253177ed20cbde4a3e5c0283cc5385b5870c8533f"},
 ]
 
 [package.dependencies]
@@ -1967,7 +1970,7 @@ sftp = ["paramiko"]
 smb = ["smbprotocol"]
 ssh = ["paramiko"]
 test = ["aiohttp (!=4.0.0a0,!=4.0.0a1)", "numpy", "pytest", "pytest-asyncio (!=0.22.0)", "pytest-benchmark", "pytest-cov", "pytest-mock", "pytest-recording", "pytest-rerunfailures", "requests"]
-test-downstream = ["aiobotocore (>=2.5.4,<3.0.0)", "dask[dataframe,test]", "moto[server] (>4,<5)", "pytest-timeout", "xarray"]
+test-downstream = ["aiobotocore (>=2.5.4,<3.0.0)", "dask-expr", "dask[dataframe,test]", "moto[server] (>4,<5)", "pytest-timeout", "xarray"]
 test-full = ["adlfs", "aiohttp (!=4.0.0a0,!=4.0.0a1)", "cloudpickle", "dask", "distributed", "dropbox", "dropboxdrivefs", "fastparquet", "fusepy", "gcsfs", "jinja2", "kerchunk", "libarchive-c", "lz4", "notebook", "numpy", "ocifs", "pandas", "panel", "paramiko", "pyarrow", "pyarrow (>=1)", "pyftpdlib", "pygit2", "pytest", "pytest-asyncio (!=0.22.0)", "pytest-benchmark", "pytest-cov", "pytest-mock", "pytest-recording", "pytest-rerunfailures", "python-snappy", "requests", "smbprotocol", "tqdm", "urllib3", "zarr", "zstandard"]
 tqdm = ["tqdm"]
 
@@ -4046,32 +4049,28 @@ typing-extensions = {version = ">=4.1.0", markers = "python_version < \"3.11\""}
 
 [[package]]
 name = "multiprocess"
-version = "0.70.17"
+version = "0.70.16"
 description = "better multiprocessing and multithreading in Python"
 optional = false
 python-versions = ">=3.8"
 groups = ["main"]
 files = [
-    {file = "multiprocess-0.70.17-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:7ddb24e5bcdb64e90ec5543a1f05a39463068b6d3b804aa3f2a4e16ec28562d6"},
-    {file = "multiprocess-0.70.17-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:d729f55198a3579f6879766a6d9b72b42d4b320c0dcb7844afb774d75b573c62"},
-    {file = "multiprocess-0.70.17-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:c2c82d0375baed8d8dd0d8c38eb87c5ae9c471f8e384ad203a36f095ee860f67"},
-    {file = "multiprocess-0.70.17-pp38-pypy38_pp73-macosx_10_9_arm64.whl", hash = "sha256:a22a6b1a482b80eab53078418bb0f7025e4f7d93cc8e1f36481477a023884861"},
-    {file = "multiprocess-0.70.17-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:349525099a0c9ac5936f0488b5ee73199098dac3ac899d81d326d238f9fd3ccd"},
-    {file = "multiprocess-0.70.17-pp38-pypy38_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:27b8409c02b5dd89d336107c101dfbd1530a2cd4fd425fc27dcb7adb6e0b47bf"},
-    {file = "multiprocess-0.70.17-pp39-pypy39_pp73-macosx_10_13_arm64.whl", hash = "sha256:2ea0939b0f4760a16a548942c65c76ff5afd81fbf1083c56ae75e21faf92e426"},
-    {file = "multiprocess-0.70.17-pp39-pypy39_pp73-macosx_10_13_x86_64.whl", hash = "sha256:2b12e081df87ab755190e227341b2c3b17ee6587e9c82fecddcbe6aa812cd7f7"},
-    {file = "multiprocess-0.70.17-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:a0f01cd9d079af7a8296f521dc03859d1a414d14c1e2b6e676ef789333421c95"},
-    {file = "multiprocess-0.70.17-py310-none-any.whl", hash = "sha256:38357ca266b51a2e22841b755d9a91e4bb7b937979a54d411677111716c32744"},
-    {file = "multiprocess-0.70.17-py311-none-any.whl", hash = "sha256:2884701445d0177aec5bd5f6ee0df296773e4fb65b11903b94c613fb46cfb7d1"},
-    {file = "multiprocess-0.70.17-py312-none-any.whl", hash = "sha256:2818af14c52446b9617d1b0755fa70ca2f77c28b25ed97bdaa2c69a22c47b46c"},
-    {file = "multiprocess-0.70.17-py313-none-any.whl", hash = "sha256:20c28ca19079a6c879258103a6d60b94d4ffe2d9da07dda93fb1c8bc6243f522"},
-    {file = "multiprocess-0.70.17-py38-none-any.whl", hash = "sha256:1d52f068357acd1e5bbc670b273ef8f81d57863235d9fbf9314751886e141968"},
-    {file = "multiprocess-0.70.17-py39-none-any.whl", hash = "sha256:c3feb874ba574fbccfb335980020c1ac631fbf2a3f7bee4e2042ede62558a021"},
-    {file = "multiprocess-0.70.17.tar.gz", hash = "sha256:4ae2f11a3416809ebc9a48abfc8b14ecce0652a0944731a1493a3c1ba44ff57a"},
+    {file = "multiprocess-0.70.16-pp310-pypy310_pp73-macosx_10_13_x86_64.whl", hash = "sha256:476887be10e2f59ff183c006af746cb6f1fd0eadcfd4ef49e605cbe2659920ee"},
+    {file = "multiprocess-0.70.16-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:d951bed82c8f73929ac82c61f01a7b5ce8f3e5ef40f5b52553b4f547ce2b08ec"},
+    {file = "multiprocess-0.70.16-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:37b55f71c07e2d741374998c043b9520b626a8dddc8b3129222ca4f1a06ef67a"},
+    {file = "multiprocess-0.70.16-pp38-pypy38_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:ba8c31889abf4511c7308a8c52bb4a30b9d590e7f58523302ba00237702ca054"},
+    {file = "multiprocess-0.70.16-pp39-pypy39_pp73-macosx_10_13_x86_64.whl", hash = "sha256:0dfd078c306e08d46d7a8d06fb120313d87aa43af60d66da43ffff40b44d2f41"},
+    {file = "multiprocess-0.70.16-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:e7b9d0f307cd9bd50851afaac0dba2cb6c44449efff697df7c7645f7d3f2be3a"},
+    {file = "multiprocess-0.70.16-py310-none-any.whl", hash = "sha256:c4a9944c67bd49f823687463660a2d6daae94c289adff97e0f9d696ba6371d02"},
+    {file = "multiprocess-0.70.16-py311-none-any.whl", hash = "sha256:af4cabb0dac72abfb1e794fa7855c325fd2b55a10a44628a3c1ad3311c04127a"},
+    {file = "multiprocess-0.70.16-py312-none-any.whl", hash = "sha256:fc0544c531920dde3b00c29863377f87e1632601092ea2daca74e4beb40faa2e"},
+    {file = "multiprocess-0.70.16-py38-none-any.whl", hash = "sha256:a71d82033454891091a226dfc319d0cfa8019a4e888ef9ca910372a446de4435"},
+    {file = "multiprocess-0.70.16-py39-none-any.whl", hash = "sha256:a0bafd3ae1b732eac64be2e72038231c1ba97724b60b09400d68f229fcc2fbf3"},
+    {file = "multiprocess-0.70.16.tar.gz", hash = "sha256:161af703d4652a0e1410be6abccecde4a7ddffd19341be0a7011b94aeb171ac1"},
 ]
 
 [package.dependencies]
-dill = ">=0.3.9"
+dill = ">=0.3.8"
 
 [[package]]
 name = "musdb"
@@ -6492,25 +6491,6 @@ design = ["optuna (>=2.10.0)"]
 docs = ["numpydoc", "sphinx (!=1.3.1)"]
 tests = ["pytest (<8)", "pytest-cov", "scipy (>=1.1)"]
 
-[[package]]
-name = "responses"
-version = "0.18.0"
-description = "A utility library for mocking out the `requests` Python library."
-optional = false
-python-versions = ">=3.7"
-groups = ["main"]
-files = [
-    {file = "responses-0.18.0-py3-none-any.whl", hash = "sha256:15c63ad16de13ee8e7182d99c9334f64fd81f1ee79f90748d527c28f7ca9dd51"},
-    {file = "responses-0.18.0.tar.gz", hash = "sha256:380cad4c1c1dc942e5e8a8eaae0b4d4edf708f4f010db8b7bcfafad1fcd254ff"},
-]
-
-[package.dependencies]
-requests = ">=2.0,<3.0"
-urllib3 = ">=1.25.10"
-
-[package.extras]
-tests = ["coverage (>=6.0.0)", "flake8", "mypy", "pytest (>=4.6)", "pytest-cov", "pytest-localserver", "types-mock", "types-requests"]
-
 [[package]]
 name = "retrying"
 version = "1.3.4"
@@ -8843,4 +8823,4 @@ type = ["pytest-mypy"]
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.10,<3.13"
-content-hash = "ffcf49c01fd9b29be1db0ee0a684e71c3ecb005f832d58dcc283089843421d16"
+content-hash = "80185c3d6c54b658a79b574f19061da7aec5bd0aeb473b9c1880c205521ec825"

whisper_diarization

@@ -0,0 +1 @@
+Subproject commit 6c9047dd7334c48acde62042890fd357117a9f55