Marvis-AI/marvis-tts-250m-v0.1-MLX-8bit

This model was converted to MLX format from Marvis-AI/marvis-tts-250m-v0.1 using mlx-audio version 0.2.5. Refer to the original model card for more details on the model.

Use with mlx

pip install -U mlx-audio

python -m mlx_audio.tts.generate --model Marvis-AI/marvis-tts-250m-v0.1-MLX-8bit --text "Describe this image."

Safetensors

Model size

207M params

Tensor type

F16

U32

Base model

Quantized

(2)

this model