deepgeek/CosyVoice
2
0
Fork 0
mirror of https://github.com/FunAudioLLM/CosyVoice.git synced 2026-02-05 18:09:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

add prompt contraint

Browse Source
This commit is contained in:
lyuxiang.lx
2024-09-05 17:09:07 +08:00
parent 4d6a55243c
commit bcda6d807c
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
cosyvoice/cli/frontend.py
View File

@@ -78,6 +78,7 @@ class CosyVoiceFrontEnd:
return text_token, text_token_len return text_token, text_token_len
def _extract_speech_token(self, speech): def _extract_speech_token(self, speech):
assert speech.shape[1] / 16000 <= 30, 'do not support extract speech token for audio longer than 30s'
feat = whisper.log_mel_spectrogram(speech, n_mels=128) feat = whisper.log_mel_spectrogram(speech, n_mels=128)
speech_token = self.speech_tokenizer_session.run(None, speech_token = self.speech_tokenizer_session.run(None,
{self.speech_tokenizer_session.get_inputs()[0].name: {self.speech_tokenizer_session.get_inputs()[0].name: