Skip to content

Update frontend.py #1474

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
wants to merge 3 commits into
base: main
Choose a base branch
from
+13 −8
Open

Update frontend.py #1474

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
063ae27
Update frontend.py
Clabiyau Jul 23, 2025
13503bc
Update frontend.py
Clabiyau Jul 23, 2025
540d80a
Update frontend.py
Clabiyau Jul 24, 2025
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
21 changes: 13 additions & 8 deletions cosyvoice/cli/frontend.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,7 @@
import os
import re
import inflect
import copy
try:
import ttsfrd
use_ttsfrd = True
Expand Down Expand Up @@ -173,33 +174,37 @@ def frontend_zero_shot(self, tts_text, prompt_text, prompt_speech_16k, resample_
'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 = copy.deepcopy(self.spk2info[zero_shot_spk_id])
if prompt_text:
prompt_text_token, prompt_text_token_len = self._extract_text_token(prompt_text)
model_input["prompt_text"] = prompt_text_token
model_input["prompt_text_len"] = prompt_text_token_len
model_input['text'] = tts_text_token
model_input['text_len'] = tts_text_token_len
return model_input

def frontend_cross_lingual(self, tts_text, prompt_speech_16k, resample_rate, zero_shot_spk_id):
model_input = self.frontend_zero_shot(tts_text, '', prompt_speech_16k, resample_rate, zero_shot_spk_id)
# in cross lingual mode, we remove prompt in llm
del model_input['prompt_text']
del model_input['prompt_text_len']
del model_input['llm_prompt_speech_token']
del model_input['llm_prompt_speech_token_len']
model_input.pop('prompt_text', None)
model_input.pop('prompt_text_len', None)
model_input.pop('llm_prompt_speech_token', None)
model_input.pop('llm_prompt_speech_token_len', None)
return model_input

def frontend_instruct(self, tts_text, spk_id, instruct_text):
model_input = self.frontend_sft(tts_text, spk_id)
# in instruct mode, we remove spk_embedding in llm due to information leakage
del model_input['llm_embedding']
model_input.pop('llm_embedding', None)
instruct_text_token, instruct_text_token_len = self._extract_text_token(instruct_text + '<endofprompt>')
model_input['prompt_text'] = instruct_text_token
model_input['prompt_text_len'] = instruct_text_token_len
return model_input

def frontend_instruct2(self, tts_text, instruct_text, prompt_speech_16k, resample_rate, zero_shot_spk_id):
model_input = self.frontend_zero_shot(tts_text, instruct_text + '<|endofprompt|>', prompt_speech_16k, resample_rate, zero_shot_spk_id)
del model_input['llm_prompt_speech_token']
del model_input['llm_prompt_speech_token_len']
model_input.pop('llm_prompt_speech_token', None)
model_input.pop('llm_prompt_speech_token_len', None)
return model_input

def frontend_vc(self, source_speech_16k, prompt_speech_16k, resample_rate):
Expand Down