Automatic Speech Recognition
MLX
Safetensors
jais_asr
jais
ifm
arabic
arabic-dialects
speech-to-text
code-switching
diacritization
language-identification
open-weights
custom_code
mlx-vlm
4-bit precision
Instructions to use IFM/Jais-ASR-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use IFM/Jais-ASR-MLX-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download IFM/Jais-ASR-MLX-4bit --local-dir Jais-ASR-MLX-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download generation_config.json from IFM/Jais-ASR-MLX-4bit: direct link, hf CLI and curl.
- Browser
- Download file 239 Bytes
-
https://huggingface.co/IFM/Jais-ASR-MLX-4bit/resolve/main/generation_config.json
- Command line
-
hf download hf://IFM/Jais-ASR-MLX-4bit/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/IFM/Jais-ASR-MLX-4bit/resolve/main/generation_config.json
239 Bytes
| { | |
| "bos_token_id": 0, | |
| "eos_token_id": [ | |
| 1, | |
| 250019 | |
| ], | |
| "pad_token_id": 0, | |
| "do_sample": false, | |
| "temperature": 0.0, | |
| "num_beams": 1, | |
| "max_new_tokens": 256, | |
| "repetition_penalty": 1.05, | |
| "transformers_version": "5.5.4" | |
| } |