Merge pull request #451 from zhuzizyf/bug-fix-split_paragraph

Merge pull request #450 from zhuzizyf/optimize-TN

Update frontend_utils.py

Update frontend_utils.py

Update frontend_utils.py

Update frontend.py

update token args

load jit to device

update vc code

update vc/tts code

add vc code

add 25hz text tokenizer

add speech fade in out

Merge pull request #379 from boji123/bj_dev_stream_fix

update tempo change

[feature] fix badcase, add fade on speech output

[refator] modify fade_in_out func to a commom form

set onnx to false as last chunk rtf unstable

add prompt contraint

fix lint

remove unnecessary code

update fastapi

add onnx export

Merge remote-tracking branch 'origin/inference_streaming' into inference_streaming

mirror modify

export onnx

Merge branch 'inference_streaming' into flow_tensorrt

mirror modify

fix bug

update

update

Merge branch 'main' into inference_streaming

revert trt TODO

add flow decoder tensorrt infer

fix vocoder speech overlap

add trt script TODO

add export script

add llm export script

chore: update encoder.py

update stream code

fix flow matching training for zero shot inference

update model inference

add stream code

Update file_utils.py

Update file_utils.py

Update frontend.py

add train cfg in flow matching

move use_spk_embedding to processor

use spk_embedding when sft

Merge branch 'main' of github.com:FunAudioLLM/CosyVoice into main