search

Edresson / YourTTS

YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone
Other
877 stars 77 forks source link

Select Speakers for Zero Shot TTS #9

Closed dipanjannC closed 2 years ago

dipanjannC commented 2 years ago

Hi ,

Firstly great work on the project with time trying to understand the repo with more clarity. Wanted to know how can I select different speakers for different sections of text .

Thanks in advance.

Edresson commented 2 years ago

Hi, I don't know if a fully understand your question. Do you want to know the test speakers set for each dataset? If it is your question I added the list of test speakers for each dataset here.

dipanjannC commented 2 years ago

Hi Edresson ,

Actually , I'm referencing your YourTTS-zeroshot-TTS-demo notebook . I want to generate two types of speakers from the speaker's list for diagloue generation . Can you help me how to tweak the config.json to do that ? Or is there something else I need to do?

Edresson commented 2 years ago

Hi, the YourTTS-zeroshot-TTS Colab notebook receives audio as a reference and generates the voice in the speaker reference voice. You just need to upload a reference for every speaker that you want and generate speech in their voice.

dipanjannC commented 2 years ago

Yes, Thanks . we can store it in different variables .

Bdw, how can we expand the language model ? suppose I want to train my model to generate hindi voices.

And is there any similarity metric to find the similarity between , real and the generated audio.