deepgeek/silero-vad
2
0
Fork 0
mirror of https://github.com/snakers4/silero-vad.git synced 2026-02-04 17:39:22 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #421 from yairl/master

Browse Source 
Perform in-place resampling during read_audio.
This commit is contained in:
Alexander Veysov
2024-02-16 09:49:28 +03:00
committed by GitHub
parent a65732a393 d391f4c302
commit af152c18f6
1 changed files with 16 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
utils_vad.py
View File

@@ -122,16 +122,24 @@ class Validator():
def read_audio(path: str,
sampling_rate: int = 16000):
wav, sr = torchaudio.load(path)
if 'sox' in torchaudio.list_available_backends():
effects = [
['channels', '1'],
['rate', str(sampling_rate)]
]
if wav.size(0) > 1:
wav = wav.mean(dim=0, keepdim=True)
wav, sr = torchaudio.sox_effects.apply_effects_file(path, effects=effects)
else:
wav, sr = torchaudio.load(path)
if sr != sampling_rate:
transform = torchaudio.transforms.Resample(orig_freq=sr,
new_freq=sampling_rate)
wav = transform(wav)
sr = sampling_rate
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
return wav.squeeze(0)