| .. |
|
bin
|
2c193781cc
fix export_onnx.py
|
hai 1 ano |
|
cli
|
587604b2b4
fix inference_instruct2 speaker ID bug
|
hai 1 ano |
|
dataset
|
65ad448714
[debug] a better solution for mismatch of speech feat len and speech token len, refer to https://github.com/FunAudioLLM/CosyVoice/issues/1051
|
hai 1 ano |
|
flow
|
65ad448714
[debug] a better solution for mismatch of speech feat len and speech token len, refer to https://github.com/FunAudioLLM/CosyVoice/issues/1051
|
hai 1 ano |
|
hifigan
|
f0b8e892f6
fix lint
|
hai 1 ano |
|
llm
|
a69b7e275d
fix vocoder train
|
hai 1 ano |
|
tokenizer
|
1298d90e48
update readme
|
hai 1 ano |
|
transformer
|
d9ffd592f6
use static_chunk_size in flow training
|
hai 1 ano |
|
utils
|
a69b7e275d
fix vocoder train
|
hai 1 ano |
|
__init__.py
|
076829ab84
add cosyvoice code
|
%!s(int64=2) %!d(string=hai) anos |
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