voice: add Marvis TTS 250m v0.2 (MLX 8bit/4bit) + Kyutai Mimi codec (CC-BY-4.0)
This commit is contained in:
parent
4cea3f7301
commit
5247c06789
38 changed files with 1657 additions and 0 deletions
28
voice/mlx/Marvis-AI/marvis-tts-250m-v0.2-MLX-8bit/README.md
Executable file
28
voice/mlx/Marvis-AI/marvis-tts-250m-v0.2-MLX-8bit/README.md
Executable file
|
|
@ -0,0 +1,28 @@
|
|||
---
|
||||
license: apache-2.0
|
||||
datasets:
|
||||
- amphion/Emilia-Dataset
|
||||
language:
|
||||
- en
|
||||
- fr
|
||||
- de
|
||||
library_name: transformers
|
||||
tags:
|
||||
- mlx
|
||||
- mlx-audio
|
||||
- transformers
|
||||
- mlx
|
||||
---
|
||||
|
||||
# Marvis-AI/marvis-tts-250m-v0.2-MLX-8bit
|
||||
This model was converted to MLX format from [`Marvis-AI/marvis-tts-250m-v0.2`](https://huggingface.co/Marvis-AI/marvis-tts-250m-v0.2) using mlx-audio version **0.2.6**.
|
||||
Refer to the [original model card](https://huggingface.co/Marvis-AI/marvis-tts-250m-v0.2) for more details on the model.
|
||||
## Use with mlx
|
||||
|
||||
```bash
|
||||
pip install -U mlx-audio
|
||||
```
|
||||
|
||||
```bash
|
||||
python -m mlx_audio.tts.generate --model Marvis-AI/marvis-tts-250m-v0.2-MLX-8bit --text "Describe this image."
|
||||
```
|
||||
Loading…
Add table
Add a link
Reference in a new issue