Instructions to use Alkd/Qwen3-ASR-1.7B-audio8-text4-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Alkd/Qwen3-ASR-1.7B-audio8-text4-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3-ASR-1.7B-audio8-text4-mlx Alkd/Qwen3-ASR-1.7B-audio8-text4-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Upload preprocessor_config.json with huggingface_hub
Browse files- preprocessor_config.json +14 -0
preprocessor_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chunk_length": 30,
|
| 3 |
+
"dither": 0.0,
|
| 4 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 5 |
+
"feature_size": 128,
|
| 6 |
+
"hop_length": 160,
|
| 7 |
+
"n_fft": 400,
|
| 8 |
+
"n_samples": 480000,
|
| 9 |
+
"nb_max_frames": 3000,
|
| 10 |
+
"padding_side": "right",
|
| 11 |
+
"padding_value": 0.0,
|
| 12 |
+
"processor_class": "Qwen3ASRProcessor",
|
| 13 |
+
"return_attention_mask": true
|
| 14 |
+
}
|