Automatic Speech Recognition
Safetensors
MLX
mlx-audio
qwen3_asr
speech-to-text
speech
transcription
asr
stt
4-bit precision
Instructions to use runfuture/Mega-ASR-MLX-Q4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use runfuture/Mega-ASR-MLX-Q4 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Mega-ASR-MLX-Q4 runfuture/Mega-ASR-MLX-Q4
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,6 +10,8 @@ tags:
|
|
| 10 |
- mlx-audio
|
| 11 |
library_name: mlx-audio
|
| 12 |
pipeline_tag: automatic-speech-recognition
|
|
|
|
|
|
|
| 13 |
---
|
| 14 |
|
| 15 |
# Mega-ASR MLX Q4
|
|
@@ -33,4 +35,4 @@ converting the merged weights to the `mlx-audio` Qwen3-ASR layout.
|
|
| 33 |
```bash
|
| 34 |
pip install -U mlx-audio
|
| 35 |
python -m mlx_audio.stt.generate --model runfuture/Mega-ASR-MLX-Q4 --audio audio.wav
|
| 36 |
-
```
|
|
|
|
| 10 |
- mlx-audio
|
| 11 |
library_name: mlx-audio
|
| 12 |
pipeline_tag: automatic-speech-recognition
|
| 13 |
+
base_model:
|
| 14 |
+
- zhifeixie/Mega-ASR
|
| 15 |
---
|
| 16 |
|
| 17 |
# Mega-ASR MLX Q4
|
|
|
|
| 35 |
```bash
|
| 36 |
pip install -U mlx-audio
|
| 37 |
python -m mlx_audio.stt.generate --model runfuture/Mega-ASR-MLX-Q4 --audio audio.wav
|
| 38 |
+
```
|