deepgeek/CosyVoice
2
0
Fork 0
mirror of https://github.com/FunAudioLLM/CosyVoice.git synced 2026-02-05 09:59:23 +08:00
Code Issues Packages Projects Releases Wiki Activity

add text_frontend arg

Browse Source
This commit is contained in:
lyuxiang.lx
2024-12-17 14:03:35 +08:00
parent 60b0416229
commit 26c774098d
3 changed files with 16 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
cosyvoice/cli/frontend.py
View File

@@ -107,12 +107,10 @@ class CosyVoiceFrontEnd:
speech_feat_len = torch.tensor([speech_feat.shape[1]], dtype=torch.int32).to(self.device)
return speech_feat, speech_feat_len
def text_normalize(self, text, split=True):
def text_normalize(self, text, split=True, text_frontend=True):
if text_frontend is False:
return [text] if split is True else text
text = text.strip()
# NOTE(lyuxiang.lx) move this judgement into ttsfrd in the future
for token in self.tokenizer.special_tokens['additional_special_tokens']:
if token in text:
return text if split is False else [text]
if contains_chinese(text):
if self.use_ttsfrd:
texts = [i["text"] for i in json.loads(self.frd.do_voicegen_frd(text))["sentences"]]