Automatic Speech Recognition
Transformers
Safetensors
English
qwen3_asr
feature-extraction
speech-recognition
asr
english
distillation
looped-transformer
parameter-sharing
qwen3-asr
custom_code
Eval Results (legacy)
Instructions to use oruk/oruk-loop-153M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use oruk/oruk-loop-153M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="oruk/oruk-loop-153M", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("oruk/oruk-loop-153M", trust_remote_code=True) model = AutoModel.from_pretrained("oruk/oruk-loop-153M", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from oruk/oruk-loop-153M: direct link, hf CLI and curl.
- Browser
- Download file 487 Bytes
-
https://huggingface.co/oruk/oruk-loop-153M/resolve/main/processor_config.json
- Command line
-
hf download hf://oruk/oruk-loop-153M/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/oruk/oruk-loop-153M/resolve/main/processor_config.json
487 Bytes
| { | |
| "feature_extractor": { | |
| "chunk_length": 30, | |
| "dither": 0.0, | |
| "feature_extractor_type": "Qwen3ASRFeatureExtractor", | |
| "feature_size": 128, | |
| "hop_length": 160, | |
| "min_length": 8000, | |
| "n_fft": 400, | |
| "n_samples": 480000, | |
| "n_window": 50, | |
| "nb_max_frames": 3000, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000 | |
| }, | |
| "processor_class": "Qwen3ASRProcessor", | |
| "timestamp_segment_time": 80 | |
| } | |