Skip to content

fix: use soundfile directly for audio loading to avoid torchaudio compatibility issues #1813

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
boomboomcaca wants to merge 1 commit into
base: main
Choose a base branch
from
+13 −1
Open

fix: use soundfile directly for audio loading to avoid torchaudio compatibility issues #1813

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 13 additions & 1 deletion cosyvoice/utils/file_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,19 @@ def read_json_lists(list_file):


def load_wav(wav, target_sr, min_sr=16000):
speech, sample_rate = torchaudio.load(wav, backend='soundfile')
import soundfile as sf
import numpy as np
# 直接使用 soundfile 加载，避免 torchaudio 兼容性问题
if isinstance(wav, (str, os.PathLike)):
data, sample_rate = sf.read(wav)
if data.ndim > 1:
data = data.mean(axis=1)
speech = torch.from_numpy(data.astype(np.float32)).unsqueeze(0)
else:
speech = wav if isinstance(wav, torch.Tensor) else torch.tensor(wav)
if speech.ndim == 1:
speech = speech.unsqueeze(0)
sample_rate = target_sr
speech = speech.mean(dim=0, keepdim=True)
if sample_rate != target_sr:
assert sample_rate >= min_sr, 'wav sample rate {} must be greater than {}'.format(sample_rate, target_sr)
Expand Down