Text-to-Speech
Safetensors
MLX
English
mlx-audio
pocket_tts
speech
speech generation
voice cloning
tts
4-bit precision
Instructions to use flyingfishinwater/pocket-tts-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use flyingfishinwater/pocket-tts-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir pocket-tts-4bit flyingfishinwater/pocket-tts-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-4.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
base_model:
|
| 6 |
+
- kyutai/pocket-tts
|
| 7 |
+
tags:
|
| 8 |
+
- mlx
|
| 9 |
+
- text-to-speech
|
| 10 |
+
- speech
|
| 11 |
+
- speech generation
|
| 12 |
+
- voice cloning
|
| 13 |
+
- tts
|
| 14 |
+
- mlx-audio
|
| 15 |
+
library_name: mlx-audio
|
| 16 |
+
---
|
| 17 |
+
# mlx-community/pocket-tts-4bit
|
| 18 |
+
|
| 19 |
+
This model was converted to MLX format from [`mlx-community/pocket-tts`](https://huggingface.co/mlx-community/pocket-tts) using mlx-audio version **0.3.0rc1**.
|
| 20 |
+
|
| 21 |
+
Refer to the [original model card](https://huggingface.co/mlx-community/pocket-tts) for more details on the model.
|
| 22 |
+
|
| 23 |
+
## Use with mlx-audio
|
| 24 |
+
|
| 25 |
+
```bash
|
| 26 |
+
pip install -U mlx-audio
|
| 27 |
+
```
|
| 28 |
+
|
| 29 |
+
### CLI Example:
|
| 30 |
+
```bash
|
| 31 |
+
python -m mlx_audio.tts.generate --model mlx-community/pocket-tts-4bit --text "Hello, this is a test."
|
| 32 |
+
```
|
| 33 |
+
|
| 34 |
+
### Python Example:
|
| 35 |
+
```python
|
| 36 |
+
from mlx_audio.tts.utils import load_model
|
| 37 |
+
from mlx_audio.tts.generate import generate_audio
|
| 38 |
+
|
| 39 |
+
model = load_model("mlx-community/pocket-tts-4bit")
|
| 40 |
+
generate_audio(
|
| 41 |
+
model=model,
|
| 42 |
+
text="Hello, this is a test.",
|
| 43 |
+
ref_audio="path_to_audio.wav",
|
| 44 |
+
file_prefix="test_audio",
|
| 45 |
+
)
|
| 46 |
+
|
| 47 |
+
```
|