Automatic Speech Recognition
Transformers
PyTorch
English
data2vec-audio
speech
hf-asr-leaderboard
Eval Results (legacy)
Eval Results
Instructions to use facebook/data2vec-audio-large-960h with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/data2vec-audio-large-960h with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="facebook/data2vec-audio-large-960h")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCTC tokenizer = AutoTokenizer.from_pretrained("facebook/data2vec-audio-large-960h") model = AutoModelForCTC.from_pretrained("facebook/data2vec-audio-large-960h", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from facebook/data2vec-audio-large-960h: direct link, hf CLI and curl.
- Browser
- Download file 256 Bytes
-
https://huggingface.co/facebook/data2vec-audio-large-960h/resolve/refs%2Fpr%2F1/preprocessor_config.json
- Command line
-
hf download hf://facebook/data2vec-audio-large-960h@refs/pr/1/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/facebook/data2vec-audio-large-960h/resolve/refs%2Fpr%2F1/preprocessor_config.json
256 Bytes
| { | |
| "do_normalize": true, | |
| "feature_extractor_type": "Wav2Vec2FeatureExtractor", | |
| "feature_size": 1, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "processor_class": "Wav2Vec2Processor", | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000 | |
| } | |