chrissewell/whisperX
1
0
Fork 0
mirror of https://github.com/m-bain/whisperX.git synced 2025-07-01 18:17:27 -04:00
Code Issues Packages Projects Releases Wiki Activity

update setup.py to install pyannote.audio==3.1.1, update diarize.py to include num_speakers; to fix Issue #592

Browse Source
This commit is contained in:
santialferez
2023-12-26 13:01:49 +01:00
parent 8540ff5985
commit 8ae6416594
15 changed files with 2366 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
whisperx/diarize.py
View File

@ -18,14 +18,14 @@ class DiarizationPipeline:
device = torch.device(device)
self.model = Pipeline.from_pretrained(model_name, use_auth_token=use_auth_token).to(device)
def __call__(self, audio: Union[str, np.ndarray], min_speakers=None, max_speakers=None):
def __call__(self, audio: Union[str, np.ndarray], num_speakers=None, min_speakers=None, max_speakers=None):
if isinstance(audio, str):
audio = load_audio(audio)
audio_data = {
'waveform': torch.from_numpy(audio[None, :]),
'sample_rate': SAMPLE_RATE
}
segments = self.model(audio_data, min_speakers=min_speakers, max_speakers=max_speakers)
segments = self.model(audio_data, num_speakers = num_speakers, min_speakers=min_speakers, max_speakers=max_speakers)
diarize_df = pd.DataFrame(segments.itertracks(yield_label=True), columns=['segment', 'label', 'speaker'])
diarize_df['start'] = diarize_df['segment'].apply(lambda x: x.start)
diarize_df['end'] = diarize_df['segment'].apply(lambda x: x.end)