Automatic Speech Recognition
MLX
Safetensors
cohere_asr
speech-recognition
transcription
audio
apple
macos
on-device
quantized
mixed-precision
3bit
4bit
custom_code
4-bit precision
Instructions to use MarkChen1214/cohere-transcribe-03-2026-MLX-Mixed-3bit4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use MarkChen1214/cohere-transcribe-03-2026-MLX-Mixed-3bit4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir cohere-transcribe-03-2026-MLX-Mixed-3bit4bit MarkChen1214/cohere-transcribe-03-2026-MLX-Mixed-3bit4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "_from_model_config": true, | |
| "bos_token_id": 4, | |
| "decoder_start_token_id": 13764, | |
| "eos_token_id": 3, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "pad_token_id": 2, | |
| "transformers_version": "5.3.0.dev0" | |
| } | |