prince-canuma commited on
Commit
b88a8ee
·
verified ·
1 Parent(s): ea30d0a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +55 -6
README.md CHANGED
@@ -3,7 +3,7 @@ license: apache-2.0
3
  language:
4
  - en
5
  base_model:
6
- - ResembleAI/chatterbox-turbo
7
  pipeline_tag: text-to-speech
8
  library_name: mlx-audio
9
  tags:
@@ -18,17 +18,66 @@ tags:
18
  # mlx-community/chatterbox-fp16
19
  This model was converted to MLX format from [`ResembleAI/chatterbox`](https://huggingface.co/ResembleAI/chatterbox) using mlx-audio version **0.2.7**.
20
  Refer to the [original model card](https://huggingface.co/ResembleAI/chatterbox) for more details on the model.
 
21
  ## Use with mlx
22
 
23
  ```bash
24
  pip install -U mlx-audio
25
  ```
26
 
27
- Voice Cloning:
28
  ```bash
29
- mlx_audio.tts.generate --model mlx-community/chatterbox-fp16 --text "Hello, this is a test of Chatterbox TTS." --ref_audio path_to_file.wav --play
30
  ```
31
- Default Voice:
 
 
 
 
 
 
 
 
 
 
 
 
32
  ```bash
33
- mlx_audio.tts.generate --model mlx-community/chatterbox-fp16 --text "Hello, this is a test of Chatterbox TTS." --play
34
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  language:
4
  - en
5
  base_model:
6
+ - ResembleAI/chatterbox
7
  pipeline_tag: text-to-speech
8
  library_name: mlx-audio
9
  tags:
 
18
  # mlx-community/chatterbox-fp16
19
  This model was converted to MLX format from [`ResembleAI/chatterbox`](https://huggingface.co/ResembleAI/chatterbox) using mlx-audio version **0.2.7**.
20
  Refer to the [original model card](https://huggingface.co/ResembleAI/chatterbox) for more details on the model.
21
+
22
  ## Use with mlx
23
 
24
  ```bash
25
  pip install -U mlx-audio
26
  ```
27
 
28
+ ### CLI Example:
29
  ```bash
30
+ python -m mlx_audio.tts.generate --model mlx-community/chatterbox-fp16 --text "Hello, this is a test."
31
  ```
32
+ ### Python Example:
33
+ ```python
34
+ from mlx_audio.tts.utils import load_model
35
+ from mlx_audio.tts.generate import generate_audio
36
+ model = load_model("mlx-community/chatterbox-fp16")
37
+ generate_audio(
38
+ model=model, text="Hello, this is a test.",
39
+ ref_audio="path_to_audio.wav",
40
+ file_prefix="test_audio",
41
+ )
42
+ ```
43
+
44
+ ### Voice Cloning:
45
  ```bash
46
+ mlx_audio.tts.generate --model mlx-community/chatterbox-fp16 --text "Hello, this is a test of Chatterbox TTS." --ref_audio path_to_file.wav --play
47
+
48
+ generate_audio(
49
+ text="Hello, this is a test of Chatterbox TTS.",
50
+ model="mlx-community/chatterbox-fp16",
51
+ ref_audio="path_to_file.wav",
52
+ ref_text="Text transcript", # Optional
53
+ file_prefix="vc_output",
54
+ )
55
+ ```
56
+
57
+ ## Multilingual Quickstart
58
+
59
+ Generate speech in 23 languages by specifying the `lang_code` parameter. The model automatically handles pronunciation, intonation, and language-specific phonemes.
60
+
61
+ ```python
62
+ from mlx_audio.tts.generate import generate_audio
63
+
64
+ generate_audio(
65
+ text="Olá, tudo bem?",
66
+ model="mlx-community/chatterbox-fp16",
67
+ lang_code="pt",
68
+ file_prefix="multilingual_output",
69
+ )
70
+ ```
71
+
72
+ ### Supported Languages
73
+
74
+ | Code | Language | Code | Language | Code | Language |
75
+ |------|------------|------|------------|------|------------|
76
+ | `ar` | Arabic | `he` | Hebrew | `no` | Norwegian |
77
+ | `da` | Danish | `hi` | Hindi | `pl` | Polish |
78
+ | `de` | German | `it` | Italian | `pt` | Portuguese |
79
+ | `el` | Greek | `ja` | Japanese | `ru` | Russian |
80
+ | `en` | English | `ko` | Korean | `sv` | Swedish |
81
+ | `es` | Spanish | `ms` | Malay | `sw` | Swahili |
82
+ | `fi` | Finnish | `nl` | Dutch | `tr` | Turkish |
83
+ | `fr` | French | `zh` | Chinese | | |