Instructions to use sourabharsh/wav2vec2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sourabharsh/wav2vec2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="sourabharsh/wav2vec2")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("sourabharsh/wav2vec2") model = AutoModelForCTC.from_pretrained("sourabharsh/wav2vec2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from sourabharsh/wav2vec2: direct link, hf CLI and curl.
- Browser
- Download file 181 Bytes
-
https://huggingface.co/sourabharsh/wav2vec2/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://sourabharsh/wav2vec2/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/sourabharsh/wav2vec2/resolve/main/tokenizer_config.json
181 Bytes
| {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"} |