deblan-mirror/buzz
1
0
Fork 0
mirror of https://github.com/chidiwilliams/buzz.git synced 2026-03-14 22:55:46 +01:00
Code Issues Projects Releases Packages Wiki Activity

Reduce duration of test audio (#214)

Browse source
This commit is contained in:
Chidi Williams 2022-12-08 05:28:12 +00:00 • committed by GitHub
commit 8f9d08ee5e
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 11 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

3
.github/workflows/ci.yml vendored
View file

@ -69,7 +69,6 @@ jobs:
matrix:
include:
- os: macos-latest
- os: ubuntu-latest
- os: windows-latest
steps:
- uses: actions/checkout@v3
@ -77,7 +76,7 @@ jobs:
submodules: recursive
- uses: actions/setup-python@v4
with:
python-version: '3.9.13'
python-version: '3.10.7'
- name: Install Poetry Action
uses: snok/install-poetry@v1.3.1

3
buzz/transcriber.py
View file

@ -194,7 +194,7 @@ class Signals(QObject):
class WhisperCppFileTranscriber(QRunnable):
signals: Signals
duration_audio_ms = sys.maxsize # max int
segments: List[Segment] = []
segments: List[Segment]
def __init__(
self,
@ -213,6 +213,7 @@ class WhisperCppFileTranscriber(QRunnable):
self.word_level_timings = word_level_timings
self.model_path = model_path
self.signals = Signals()
self.segments = []
self.process = QProcess()
self.process.readyReadStandardError.connect(self.read_std_err)

BIN
testdata/whisper-french.mp3 vendored
View file

Binary file not shown.

2
tests/gui_test.py
View file

@ -187,7 +187,7 @@ class TestFileTranscriberWidget:
widget.run_button.click()
output_file = open(output_file_path, 'r', encoding='utf-8')
assert 'Bienvenue dans Passe-Relle, un podcast' in output_file.read()
assert 'Bienvenue dans Passe' in output_file.read()
class TestSettings:

14
tests/transcriber_test.py
View file

@ -41,8 +41,8 @@ class TestWhisperCppFileTranscriber:
@pytest.mark.parametrize(
'task,output_text',
[
(Task.TRANSCRIBE, 'Bienvenue dans Passe-Relle, un podcast'),
(Task.TRANSLATE, 'Welcome to Passe-Relle, a podcast'),
(Task.TRANSCRIBE, 'Bienvenue dans Passe'),
(Task.TRANSLATE, 'Welcome to Passe-Relle'),
])
def test_transcribe(self, qtbot, tmp_path: pathlib.Path, task: Task, output_text: str):
output_file_path = tmp_path / 'whisper_cpp.txt'
@ -84,11 +84,11 @@ class TestWhisperFileTranscriber:
@pytest.mark.parametrize(
'word_level_timings,output_format,output_text',
[
(False, OutputFormat.TXT, 'Bienvenue dans Passe-Relle, un podcast'),
(False, OutputFormat.SRT, '1\n00:00:00.000 --> 00:00:06.560\n Bienvenue dans Passe-Relle, un podcast pensé pour évêyer la curiosité des apprenances'),
(False, OutputFormat.VTT, 'WEBVTT\n\n00:00:00.000 --> 00:00:06.560\n Bienvenue dans Passe-Relle, un podcast pensé pour évêyer la curiosité des apprenances'),
(False, OutputFormat.TXT, 'Bienvenue dans Passe-Relle'),
(False, OutputFormat.SRT, '1\n00:00:00.000 --> 00:00:06.560\n Bienvenue dans Passe-Relle'),
(False, OutputFormat.VTT, 'WEBVTT\n\n00:00:00.000 --> 00:00:06.560\n Bienvenue dans Passe'),
(True, OutputFormat.SRT,
'1\n00:00:00.040 --> 00:00:00.359\n Bienvenue dans\n\n2\n00:00:00.359 --> 00:00:00.419\n Passe-'),
'1\n00:00:00.040 --> 00:00:00.299\n Bien\n\n2\n00:00:00.299 --> 00:00:00.329\nvenue dans\n\n3\n00:00:00.329 --> 00:00:00.429\n P\n\n4\n00:00:00.429 --> 00:00:00.589\nasse-'),
])
def test_transcribe(self, qtbot, tmp_path: pathlib.Path, word_level_timings: bool, output_format: OutputFormat, output_text: str):
output_file_path = tmp_path / f'whisper.{output_format.value.lower()}'
@ -161,4 +161,4 @@ class TestWhisperCpp:
result = whisper_cpp.transcribe(
audio='testdata/whisper-french.mp3', params=params)
assert 'Bienvenue dans Passe-Relle, un podcast' in result['text']
assert 'Bienvenue dans Passe' in result['text']