deepgeek/CosyVoice
2
0
Fork 0
mirror of https://github.com/FunAudioLLM/CosyVoice.git synced 2026-02-04 17:39:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix bug

Browse Source
This commit is contained in:
lyuxiang.lx
2025-12-29 10:30:54 +00:00
parent 4d7295a9a7
commit 3b44913782
5 changed files with 10 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
cosyvoice/cli/cosyvoice.py
View File

@@ -89,6 +89,8 @@ class CosyVoice:
start_time = time.time()
def inference_zero_shot(self, tts_text, prompt_text, prompt_wav, zero_shot_spk_id='', stream=False, speed=1.0, text_frontend=True):
if self.__class__.__name__ == 'CosyVoice3' and '<|endofprompt|>' not in prompt_text + tts_text:
logging.warning('<|endofprompt|> not found in CosyVoice3 inference, check your input text')
prompt_text = self.frontend.text_normalize(prompt_text, split=False, text_frontend=text_frontend)
for i in tqdm(self.frontend.text_normalize(tts_text, split=True, text_frontend=text_frontend)):
if (not isinstance(i, Generator)) and len(i) < 0.5 * len(prompt_text):

2
cosyvoice/cli/frontend.py
View File

@@ -183,7 +183,7 @@ class CosyVoiceFrontEnd:
'prompt_speech_feat': speech_feat, 'prompt_speech_feat_len': speech_feat_len,
'llm_embedding': embedding, 'flow_embedding': embedding}
else:
model_input = self.spk2info[zero_shot_spk_id]
model_input = {**self.spk2info[zero_shot_spk_id]}
model_input['text'] = tts_text_token
model_input['text_len'] = tts_text_token_len
return model_input