Are you adding the New SOTA F5-TTS. This is really impressive

erew123 / alltalk_tts

AllTalk is based on the Coqui TTS engine, similar to the Coqui_tts extension for Text generation webUI, however supports a variety of advanced features, such as a settings page, low VRAM support, DeepSpeed, narrator, model finetuning, custom models, wav file maintenance. It can also be used with 3rd Party software via JSON calls.

GNU Affero General Public License v3.0

1.16k stars 122 forks source link

Are you adding the New SOTA F5-TTS. This is really impressive #371

Closed maxbizz closed 1 month ago

maxbizz commented 1 month ago

Github: https://github.com/SWivid/F5-TTS Paper: F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching Demonstrations: https://swivid.github.io/F5-TTS/

Model Weights: https://huggingface.co/SWivid/F5-TTS

Im really impressed with this model. Its better than Xttx -v2 in my opinion. Are you considering adding it to your awesome repo?

aziib commented 1 month ago

i need this too, i hope the dev will consider this.

erew123 commented 1 month ago

Hi @maxbizz @aziib

I have seen this and would like to take a shot at adding it at some point. However, it will be a little while away, reasons are explained here.

I have added this to the feature request list https://github.com/erew123/alltalk_tts/discussions/74

Thanks