j-csc commited on
Commit
a6af09a
1 Parent(s): f63d880

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +32 -0
README.md CHANGED
@@ -1,3 +1,35 @@
1
  ---
2
  license: mit
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: mit
3
+ language:
4
+ - en
5
+ library_name: mlx
6
+ pipeline_tag: text-to-speech
7
+ tags:
8
+ - nlp
9
+ - tts
10
+ - bark
11
  ---
12
+
13
+ ## Model Summary
14
+
15
+ Bark is a transformer based text-to-audio model that can generate speech and miscellaneous audio i.e. background noise / music.
16
+
17
+ 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.
18
+
19
+ This repository contains the Bark weights in `npz` format suitable for use with Apple's MLX Framework.
20
+
21
+ ## Usage
22
+
23
+ ```bash
24
+ # Setup
25
+ pip install transformers huggingface_hub hf_transfer
26
+ git clone https://github.com/j-csc/mlx_bark
27
+ cd mlx_bark
28
+ pip install -r requirements.txt
29
+
30
+ # Download model
31
+ export HF_HUB_ENABLE_HF_TRANSFER=1
32
+ huggingface-cli download --local-dir-use-symlinks False --local-dir weights/ mlx-community/mlx_bark
33
+
34
+ # Run example (large model)
35
+ python model.py --text="Hello world!" --path weights/ --model large