deepgeek/silero-vad
2
0
Fork 0
mirror of https://github.com/snakers4/silero-vad.git synced 2026-02-05 18:09:22 +08:00
Code Issues Packages Projects Releases Wiki Activity

Use SoX when possible for loading a file with in-place resampling, ffmpeg otherwise.

Browse Source
This commit is contained in:
Yair Lifshitz
2024-02-15 12:25:22 -05:00
parent bf18ea6b56
commit d391f4c302
1 changed files with 17 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
utils_vad.py
View File

@@ -122,12 +122,24 @@ class Validator():
def read_audio(path: str, def read_audio(path: str,
sampling_rate: int = 16000): sampling_rate: int = 16000):
effects = [ if 'sox' in torchaudio.list_available_backends():
['channels', '1'], effects = [
['rate', str(sampling_rate)] ['channels', '1'],
] ['rate', str(sampling_rate)]
]
wav, sr = torchaudio.sox_effects.apply_effects_file(path, effects=effects) wav, sr = torchaudio.sox_effects.apply_effects_file(path, effects=effects)
else:
wav, sr = torchaudio.load(path)
if wav.size(0) > 1:
wav = wav.mean(dim=0, keepdim=True)
if sr != sampling_rate:
transform = torchaudio.transforms.Resample(orig_freq=sr,
new_freq=sampling_rate)
wav = transform(wav)
sr = sampling_rate
assert sr == sampling_rate assert sr == sampling_rate
return wav.squeeze(0) return wav.squeeze(0)