Veyron-G comments

Repositories
Issues
Comments

Results 4 comments of


                                            Veyron-G

What should I do to make fish-speech support streaming input?

> any luck? we are trying the same too You can try to use websocket.

feat: support qwen_2_5_omni fine-tuning

> Talker模块我们正在加紧研究，今明应该可以弄好text-audio输入的微调～ talker模块现在可以支持更换音色吗比如用一些其他的音色微调

The expanded size of the tensor (472) must match the existing size (1023) at non-singleton dimension 1.

> This patch can fix the bug. > > ``` > --- a/tools/llama/generate.py > +++ b/tools/llama/generate.py > @@ -263,13 +263,15 @@ def generate( > model, > next_token.view(1, codebook_dim, -1), >...

视频处理问题

> 我debug发现是from musetalk.utils.face_detection import FaceAlignment,LandmarksType导入的时候一直卡住，请问有好的解决办法吗？ +++++++1