Automatic Speech Recognition
Transformers
TensorBoard
ONNX
Safetensors
English
whisper
audio
Eval Results
Instructions to use algorithco/distil-large-v3.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use algorithco/distil-large-v3.5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="algorithco/distil-large-v3.5")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("algorithco/distil-large-v3.5") model = AutoModelForSpeechSeq2Seq.from_pretrained("algorithco/distil-large-v3.5", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from algorithco/distil-large-v3.5: direct link, hf CLI and curl.
- Browser
- Download file 340 Bytes
-
https://huggingface.co/algorithco/distil-large-v3.5/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://algorithco/distil-large-v3.5/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/algorithco/distil-large-v3.5/resolve/main/preprocessor_config.json
340 Bytes
| { | |
| "chunk_length": 30, | |
| "feature_extractor_type": "WhisperFeatureExtractor", | |
| "feature_size": 128, | |
| "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 | |
| } | |