Text to Speech MLX model.

[javileyes]

There are MLX models for text generation (llama 3) and for text recognition (whisper) but I think that to have a complete NLP environment it would be necessary to create a text to scpeech MLX. How would it be possible to create, for example, an MLX model of facebook/fastspeech2-en-ljspeech?

[awni]

It should be possible. There is a port of Suno's Bark model already: https://github.com/j-csc/mlx_bark

I think it still depends on PyTorch for the encodec model though.