Instructions to use rav2040/wav2vec2-base-timit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rav2040/wav2vec2-base-timit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="rav2040/wav2vec2-base-timit")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("rav2040/wav2vec2-base-timit") model = AutoModelForCTC.from_pretrained("rav2040/wav2vec2-base-timit", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from rav2040/wav2vec2-base-timit: direct link, hf CLI and curl.
- Browser
- Download file 236 Bytes
-
https://huggingface.co/rav2040/wav2vec2-base-timit/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://rav2040/wav2vec2-base-timit/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/rav2040/wav2vec2-base-timit/resolve/main/tokenizer_config.json
236 Bytes
| { | |
| "bos_token": "<s>", | |
| "do_lower_case": false, | |
| "eos_token": "</s>", | |
| "pad_token": "[PAD]", | |
| "replace_word_delimiter_char": " ", | |
| "tokenizer_class": "Wav2Vec2CTCTokenizer", | |
| "unk_token": "[UNK]", | |
| "word_delimiter_token": "|" | |
| } | |