deepgeek/CosyVoice
2
0
Fork 0
mirror of https://github.com/FunAudioLLM/CosyVoice.git synced 2026-02-05 01:49:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

add llm bistream

Browse Source
This commit is contained in:
lyuxiang.lx
2025-01-23 10:12:06 +08:00
parent 0b75c3a03f
commit 07e477519b
10 changed files with 163 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tools/extract_speech_token.py
View File

@@ -24,7 +24,7 @@ import whisper
def single_job(utt):
audio, sample_rate = torchaudio.load(utt2wav[utt])
audio, sample_rate = torchaudio.load(utt2wav[utt], backend='soundfile')
if sample_rate != 16000:
audio = torchaudio.transforms.Resample(orig_freq=sample_rate, new_freq=16000)(audio)
if audio.shape[1] / 16000 > 30: