metadata
license: mit
language:
- en
library_name: mlx
pipeline_tag: text-to-speech
tags:
- nlp
- tts
- bark
Model Summary
Bark is a transformer based text-to-audio model that can generate speech and miscellaneous audio i.e. background noise / music.
This is a port of Suno's Bark model in Apple's ML Framework, MLX. The intention of the port is to explore the potential in making fast on-device TTS inference possible.
This repository contains the Bark weights in npz format suitable for use with Apple's MLX Framework.
Usage
# Setup
pip install transformers huggingface_hub hf_transfer
git clone https://github.com/j-csc/mlx_bark
cd mlx_bark
pip install -r requirements.txt
# Download model
export HF_HUB_ENABLE_HF_TRANSFER=1
huggingface-cli download --local-dir-use-symlinks False --local-dir weights/ mlx-community/mlx_bark
# Run example (large model)
python model.py --text="Hello world!" --path weights/ --model large