Rishabh Jain

icon indicating a website link rishabhjain16.github.io icon indicating an email [email protected]

icon location Ireland icon location AI in Speech, Text-To-Speech, Speech-To-Text, Large Language Models

Results 9 comments of Rishabh Jain

F0 Converter for P - loss function values

Thank you for your quick response.I understand what you are saying. I found that in the appendix of paper. What I meant to ask are the 2 values you are...

F0 Converter for P - loss function values

Thanks for your help. Paper covered most of my doubts. Great read.

[FastPitch1.1/pytorch] "estimate_pitch" in the data_function.py is a bad function

Did you find any workaround for this? I think I might be stuck due to this issue. #1200

Problem running the speaker embedding network while training from scratch.

I would also appreciate if you have any documentation for training from scratch. I am sure it will also help the others who try to implement your work from the...

Problem running the speaker embedding network while training from scratch.

Hi @caizexin, Thank you so much for your help and getting back to me. > Hi Rishabh, I assume you are running the code on a Windows system. The error...

Problem running the speaker embedding network while training from scratch.

Just to give you an update, I started my encoder training again using **Docker Ubuntu machine** and my model seems to be working on it. I still have some doubts...

Problem running the speaker embedding network while training from scratch.

Got it. Thanks a ton. I will try it out over the windows machine to see if I coud figure out the problem. I have another query which I have...

Problem running the speaker embedding network while training from scratch.

Okay. I will do that. Thanks

One-hot code speaker embedding and GE2E speaker embedding.

Hi @CODEJIN, Thank you for your response. And thank you for clarifying my doubts. SpeechSplit process seems to be quite interesting to me in the way they are extracting the...