transformers.js icon indicating copy to clipboard operation
transformers.js copied to clipboard
verified publisher icon xenova

Request to support suno-ai/bark model

Open ttys026 opened this issue 1 year ago • 3 comments

Model description

model github model huggingface

Prerequisites

  • [X] The model is supported in Transformers (i.e., listed here)
  • [ ] The model can be exported to ONNX with Optimum (i.e., listed here)

Additional information

Sorry I am pretty new to this field, I am not sure if this model is supported to be exported as ONNX format. This model generate highly realistic speech, and has great multilingual ability.

Your contribution

...

ttys026 avatar May 20 '24 19:05 ttys026

Is this the model that can generate sounds / sound effects? If so, I'd dig support for it too, as a companion to Musicgen.

flatsiedatsie avatar May 22 '24 11:05 flatsiedatsie

I opened a feature request to Optimum quite some time ago: https://github.com/huggingface/optimum/issues/1214. Adding support there is a prerequisite for Transformers.js support :)

xenova avatar May 23 '24 00:05 xenova

It seems Stable AI has also released a new sound effects model a few weeks ago: https://huggingface.co/stabilityai/stable-audio-open-1.0

flatsiedatsie avatar Jun 17 '24 10:06 flatsiedatsie