 lyuxiang.lx
|
cbfed4a9ee
send streaming as args
|
6 months ago |
|
lyuxiang.lx
|
68100c267a
remove flow_cache
|
6 months ago |
 burkliu
|
65ad448714
[debug] a better solution for mismatch of speech feat len and speech token len, refer to https://github.com/FunAudioLLM/CosyVoice/issues/1051
|
7 months ago |
|
lyuxiang.lx
|
a69b7e275d
fix vocoder train
|
9 months ago |
|
lyuxiang.lx
|
2a3e033ee1
fix lint
|
10 months ago |
|
lyuxiang.lx
|
fd1a951a6c
add flow unified training
|
10 months ago |
|
lyuxiang.lx
|
1c062ab381
add flow decoder cache
|
10 months ago |
|
lyuxiang.lx
|
77d8cf13a3
update
|
11 months ago |
|
lyuxiang.lx
|
ac70560364
fix lint
|
11 months ago |
|
lyuxiang.lx
|
2345ce6be2
update
|
11 months ago |
|
lyuxiang.lx
|
3e381002d7
add cosyvoice2
|
11 months ago |
|
lyuxiang.lx
|
a4db3db8ed
update flow cache
|
1 year ago |
|
boji123
|
8130abb5ea
[debug] handle cache with prompt
|
1 year ago |
|
boji123
|
c9acce1482
[debug] support flow cache, for sharper tts_mel output
|
1 year ago |
|
lyuxiang.lx
|
72b89a52fb
update vc/tts code
|
1 year ago |
|
lyuxiang.lx
|
49015f63e6
add vc code
|
1 year ago |
|
lyuxiang.lx
|
90433f5373
fix lint
|
1 year ago |
|
lyuxiang.lx
|
e141634da1
remove unnecessary code
|
1 year ago |
|
Xiang Lyu
|
ee988420f3
Merge branch 'inference_streaming' into flow_tensorrt
|
1 year ago |
 zhoubofan.zbf
|
53a3c1b17f
update
|
1 year ago |
|
Xiang Lyu
|
662012999a
Merge branch 'main' into inference_streaming
|
1 year ago |
|
lyuxiang.lx
|
f4e70e222c
update stream code
|
1 year ago |
|
lyuxiang.lx
|
9504c3f88b
fix flow matching training for zero shot inference
|
1 year ago |
|
lyuxiang.lx
|
0fd15bb12b
use spk_embedding when sft
|
1 year ago |
|
lyuxiang.lx
|
076829ab84
add cosyvoice code
|
1 year ago |
