Automatic Speech Recognition
MLX
ONNX
Safetensors
asr
speech-recognition
robust-asr
quantized
int4
4bit
mixed-precision
dwq
on-device
apple-silicon
qwen3
qwen3-asr
mega-asr
Instructions to use Reza2kn/mega-asr-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Reza2kn/mega-asr-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir mega-asr-mlx Reza2kn/mega-asr-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
Add mixed 8-bit attn + 4-bit MLP variant (92.2%)
Browse files- .gitattributes +1 -0
- mlx/llm-mixed8_4/tokenizer.json +3 -0
.gitattributes
CHANGED
|
@@ -42,3 +42,4 @@ examples/mixed.wav filter=lfs diff=lfs merge=lfs -text
|
|
| 42 |
examples/noise.wav filter=lfs diff=lfs merge=lfs -text
|
| 43 |
examples/obstructed.wav filter=lfs diff=lfs merge=lfs -text
|
| 44 |
examples/recording.wav filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 42 |
examples/noise.wav filter=lfs diff=lfs merge=lfs -text
|
| 43 |
examples/obstructed.wav filter=lfs diff=lfs merge=lfs -text
|
| 44 |
examples/recording.wav filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
mlx/llm-mixed8_4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
mlx/llm-mixed8_4/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe1fad59be22a41ee293363fcf95fdedbc7c93f3b49270b1d2e18bd1399a7a05
|
| 3 |
+
size 11429653
|