Instructions to use Ramnathan/wav2vec2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ramnathan/wav2vec2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Ramnathan/wav2vec2")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("Ramnathan/wav2vec2") model = AutoModelForCTC.from_pretrained("Ramnathan/wav2vec2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from Ramnathan/wav2vec2: direct link, hf CLI and curl.
- Browser
- Download file 379 Bytes
-
https://huggingface.co/Ramnathan/wav2vec2/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://Ramnathan/wav2vec2/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/Ramnathan/wav2vec2/resolve/main/tokenizer_config.json
379 Bytes
| {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": true, "word_delimiter_token": "|", "special_tokens_map_file": "/home/patrick/hugging_face/add_wav2vec/hf/wav2vec2-large-xlsr-53-french/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "/home/patrick/hugging_face/add_wav2vec/hf/wav2vec2-large-xlsr-53-french"} | |