Transformers
Safetensors
whisper
ASR
Automatic Speech Recognition
Whisper
Medusa
Speech
Speculative Decoding
Instructions to use aiola/whisper-medusa-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use aiola/whisper-medusa-v1 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("aiola/whisper-medusa-v1") model = AutoModel.from_pretrained("aiola/whisper-medusa-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from aiola/whisper-medusa-v1: direct link, hf CLI and curl.
- Browser
- Download file 339 Bytes
-
https://huggingface.co/aiola/whisper-medusa-v1/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://aiola/whisper-medusa-v1/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/aiola/whisper-medusa-v1/resolve/main/preprocessor_config.json
339 Bytes
| { | |
| "chunk_length": 30, | |
| "feature_extractor_type": "WhisperFeatureExtractor", | |
| "feature_size": 80, | |
| "hop_length": 160, | |
| "n_fft": 400, | |
| "n_samples": 480000, | |
| "nb_max_frames": 3000, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "processor_class": "WhisperProcessor", | |
| "return_attention_mask": false, | |
| "sampling_rate": 16000 | |
| } | |