Instructions to use hr16/omniASR_CTC_3B_fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hr16/omniASR_CTC_3B_fp16 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="hr16/omniASR_CTC_3B_fp16")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("hr16/omniASR_CTC_3B_fp16") model = AutoModelForCTC.from_pretrained("hr16/omniASR_CTC_3B_fp16", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from hr16/omniASR_CTC_3B_fp16: direct link, hf CLI and curl.
- Browser
- Download file 213 Bytes
-
https://huggingface.co/hr16/omniASR_CTC_3B_fp16/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://hr16/omniASR_CTC_3B_fp16/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/hr16/omniASR_CTC_3B_fp16/resolve/main/preprocessor_config.json
213 Bytes
| { | |
| "do_normalize": true, | |
| "feature_extractor_type": "Wav2Vec2FeatureExtractor", | |
| "feature_size": 1, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000 | |
| } |