Feature Extraction
MLX
Safetensors
Chinese
English
audio
speech
codec
tokenizer
apple-silicon
quantized
8bit
Instructions to use mlx-community/MOSS-Audio-Tokenizer-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/MOSS-Audio-Tokenizer-MLX-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir MOSS-Audio-Tokenizer-MLX-8bit mlx-community/MOSS-Audio-Tokenizer-MLX-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Sync model card
Browse files
README.md
CHANGED
|
@@ -55,7 +55,7 @@ model = MossAudioTokenizerModel.from_path("mlx-int8")
|
|
| 55 |
The tokenizer is loaded automatically when you run OpenMOSS generation scripts. You usually do not need to instantiate it directly.
|
| 56 |
|
| 57 |
```bash
|
| 58 |
-
python scripts/
|
| 59 |
--text "Hello from mlx-speech." \
|
| 60 |
--output outputs/out.wav
|
| 61 |
```
|
|
|
|
| 55 |
The tokenizer is loaded automatically when you run OpenMOSS generation scripts. You usually do not need to instantiate it directly.
|
| 56 |
|
| 57 |
```bash
|
| 58 |
+
python scripts/generate/moss_local.py \
|
| 59 |
--text "Hello from mlx-speech." \
|
| 60 |
--output outputs/out.wav
|
| 61 |
```
|