Spaces:
Running
on
Zero
Running
on
Zero
Commit History
add prompt contraint
bcda6d8
fix lint
90433f5
remove unnecessary code
e141634
update fastapi
7555afb
add onnx export
2ce7240
Merge remote-tracking branch 'origin/inference_streaming' into inference_streaming
752103a
禾息
commited on
mirror modify
a801416
禾息
commited on
export onnx
fadb220
禾息
commited on
Merge branch 'inference_streaming' into flow_tensorrt
ee98842
unverified
mirror modify
18599be
禾息
commited on
fix bug
2940836
zhoubofan.zbf
commited on
update
6e7f5b9
禾息
commited on
update
53a3c1b
zhoubofan.zbf
commited on
Merge branch 'main' into inference_streaming
6620129
unverified
revert trt TODO
1ab3186
add flow decoder tensorrt infer
5f21aef
zhoubofan.zbf
commited on
fix vocoder speech overlap
1d881df
add trt script TODO
f1e374a
add export script
8b097f7
add llm export script
9ab298d
chore: update encoder.py
a44bf2b
unverified
update stream code
f4e70e2
fix flow matching training for zero shot inference
9504c3f
update model inference
02f941d
add stream code
a13411c
Update file_utils.py
f2939a9
unverified
刘悦
commited on
Update file_utils.py
cf43100
unverified
刘悦
commited on
Update frontend.py
6ae6ba3
unverified
zhuyunfeng
commited on
add train cfg in flow matching
44aea80
move use_spk_embedding to processor
6cebcb3
use spk_embedding when sft
0fd15bb
Merge branch 'main' of github.com:FunAudioLLM/CosyVoice into main
a723ea3
add constant lr scheduler
793a248
FIX: 修复自然语言控制生成音频时发生错误，异常信息如下：AttributeError: 'CosyVoiceFrontEnd' object has no attribute 'en_tn_model'
225b56d
cyz
commited on
keep only embedding mean as spk embedding
6a3e442
add empty cache
ee9e87b
add WeTextProcessing
7981796
没有标点结尾时默认加上句号
69026d8
passerbya
commited on
文本中没有标点时无法合成
f9fe31f
passerbya
commited on
优先使用ttsfrd，ttsfrd不存在时使用WeTextProcessing
95b8866
passerbya
commited on
更换前端为WeTextProcessing
88c8bf7
unverified
passerbya
commited on
半角句号会导致合成失败：RuntimeError: torch.cat(): expected a non-empty list of Tensors
2f49610
unverified
passerbya
commited on