Instructions to use nooobedd/wav2vec_custom with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nooobedd/wav2vec_custom with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="nooobedd/wav2vec_custom")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("nooobedd/wav2vec_custom") model = AutoModelForCTC.from_pretrained("nooobedd/wav2vec_custom", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from nooobedd/wav2vec_custom: direct link, hf CLI and curl.
- Browser
- Download file 337 Bytes
-
https://huggingface.co/nooobedd/wav2vec_custom/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://nooobedd/wav2vec_custom/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/nooobedd/wav2vec_custom/resolve/main/tokenizer_config.json
337 Bytes
| { | |
| "bos_token": "<s>", | |
| "do_lower_case": false, | |
| "eos_token": "</s>", | |
| "name_or_path": "42MARU/ko-spelling-wav2vec2-conformer-del-1s", | |
| "pad_token": "<pad>", | |
| "replace_word_delimiter_char": " ", | |
| "special_tokens_map_file": null, | |
| "tokenizer_class": "Wav2Vec2CTCTokenizer", | |
| "unk_token": "<unk>", | |
| "word_delimiter_token": "|" | |
| } | |