deblan-mirror/buzz
1
0
Fork 0
mirror of https://github.com/chidiwilliams/buzz.git synced 2026-03-16 23:55:51 +01:00
Code Issues Projects Releases Packages Wiki Activity

Adding speech extraction option to CLI (#1311)

Browse source
This commit is contained in:
Raivis Dejus 2025-12-13 08:05:55 +02:00 • committed by GitHub
commit dc0dc6b3d2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 8 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

6
buzz/cli.py
View file

@ -102,6 +102,9 @@ def parse(app: Application, parser: QCommandLineParser):
word_timestamp_option = QCommandLineOption(
["w", "word-timestamps"], "Generate word-level timestamps."
)
extract_speech_option = QCommandLineOption(
["e", "extract-speech"], "Extract speech from audio before transcribing."
)
open_ai_access_token_option = QCommandLineOption(
"openai-token",
f"OpenAI access token. Use only when --model-type is {CommandLineModelType.OPEN_AI_WHISPER_API.value}. Defaults to your previously saved access token, if one exists.",
@ -124,6 +127,7 @@ def parse(app: Application, parser: QCommandLineParser):
language_option,
initial_prompt_option,
word_timestamp_option,
extract_speech_option,
open_ai_access_token_option,
output_directory_option,
srt_option,
@ -178,6 +182,7 @@ def parse(app: Application, parser: QCommandLineParser):
initial_prompt = parser.value(initial_prompt_option)
word_timestamps = parser.isSet(word_timestamp_option)
extract_speech = parser.isSet(extract_speech_option)
output_formats: typing.Set[OutputFormat] = set()
if parser.isSet(srt_option):
@ -205,6 +210,7 @@ def parse(app: Application, parser: QCommandLineParser):
language=language,
initial_prompt=initial_prompt,
word_level_timings=word_timestamps,
extract_speech=extract_speech,
openai_access_token=openai_access_token,
)

3
docs/docs/cli.md
View file

@ -60,7 +60,8 @@ Options:
(Yiddish), yo (Yoruba), zh (Chinese). Leave
empty to detect language.
-p, --prompt <prompt> Initial prompt.
-w, --word-timestamps Generate word-level timestamps. (available since 1.2.0)
-w, --word-timestamps Generate word-level timestamps. (available since 1.2.0)
-e, --extract-speech Extract speech from audio before transcribing. (available since 1.3.0)
--openai-token <token> OpenAI access token. Use only when
--model-type is openaiapi. Defaults to your
previously saved access token, if one exists.