furqan ali

Is there any plan to release expressive TTS like SeamlessExpressive model from Meta?

3

**🚀 Feature Description** Hi is there any plan to release expressive TTS like SeamlessExpressive model from Meta? The model which can keep the underlying tonality, breaks, and expressions of the...

I got the error while runing python main.py, could you please advise.

1

Error log: (FuSta_CVPR2020) azureuser@transpifytts:~/FuSta/CVPR2020CODE_yulunliu_modified$ python main.py ../input_frames/ ../CVPR2020_output/ ../CVPR2020_warping_field/ Loading weights for net_encoder Loading weights for net_decoder loaded!!!!!!!!!!!!!!!!! ../input_frames/ 1.0 0.99999994 1.0000001 THCudaCheck FAIL file=/pytorch/aten/src/THC/THCGeneral.cpp line=405 error=8 : invalid device...

Any male person voice available or only we can have female voices?

4

Hi, first of all kudos to your great work. Such a marvelous job done here. Thank you so much for such wonderful contribution. I was wondering can i change speaker...

The docker file is broken

2

Docker isn't building successfully

 As you can see there is no such path available in check point folder as per your demo_par3. could you please double check

How to control emotions?

2

First of all great work. Where many companies launch the stuff as close source. You guys are true example of open source contribution towards better AI. Secondly I had a...

It's not even nearly close to good.

3

I tried to clone many voices but it failed all the time. Was just spitting out a useless cloned voice and sometime not even speaking properly.

where to get the kmeans_path = './path/to/hubert/kmeans.bin file?

7

I tried to look this file in fairseq repo but I couldn't find. Could you please point out where we can download kmeans.bin file? kmeans_path = './path/to/hubert/kmeans.bin

mecab-python3 errors.. popping up.

1

I don't know how to solve this. I have tried every solution on the internet and I am pissed off.