Request for access training dataset

[hungdinhxuan]

Hello, I've been reading your paper and am very interested in your project. I noticed that the paper mentions the use of a MSML for training the model, but it doesn't specify the exact dataset used. I'm particularly interested in the emotion-style speech data that you've collected. This is a unique and valuable resource, and I'd love to learn more about it. Could you share with us access permission to your training dataset?

Thank you for your work on this project.

[Zengyi-Qin]

Hi - We are actually workinig on a new project that will opensource the data (with diverse emotion/styles) and code. Stay tuned!

[xvdp]

I second the request for training codes - or fine tuning codes. I think those are more important than the dataset in the first instance. Thank you

[dustysys]

Ability to finetune would be great, somewhat limited as things are.

[hildazzz]

mark

[lyzhang1999]

mark

[Sovenok-Hacker]

I also look forward to source code release

[tchayintr]

Looking forward to the code, especially for fine-tuning it for a Southeast Asian language, in relation to your concept.

[yunjiallm]

Hi - We are actually workinig on a new project that will opensource the data (with diverse emotion/styles) and code. Stay tuned!

When will this work be finished and open sourced

[ismailgokhanuslu]

i also look forward to. i want to add a turkish language base speaker and i think this is what i need. since i am voip engineer and already running a callcenter application which my team developped, we will have adequate dataset