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

new logic, diarization, vad filtering

Browse Source
This commit is contained in:
Max Bain
2023-01-24 15:02:08 +00:00
parent ba102feb7f
commit d395c21b83
8 changed files with 498 additions and 260 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
whisperx/audio.py
View File

@ -113,7 +113,7 @@ def log_mel_spectrogram(audio: Union[str, np.ndarray, torch.Tensor], n_mels: int
window = torch.hann_window(N_FFT).to(audio.device)
stft = torch.stft(audio, N_FFT, HOP_LENGTH, window=window, return_complex=True)
magnitudes = stft[:, :-1].abs() ** 2
magnitudes = stft[..., :-1].abs() ** 2
filters = mel_filters(audio.device, n_mels)
mel_spec = filters @ magnitudes
@ -121,4 +121,4 @@ def log_mel_spectrogram(audio: Union[str, np.ndarray, torch.Tensor], n_mels: int
log_spec = torch.clamp(mel_spec, min=1e-10).log10()
log_spec = torch.maximum(log_spec, log_spec.max() - 8.0)
log_spec = (log_spec + 4.0) / 4.0
return log_spec
return log_spec