Instructions to use esc-benchmark/wav2vec2-ctc-gigaspeech with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use esc-benchmark/wav2vec2-ctc-gigaspeech with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="esc-benchmark/wav2vec2-ctc-gigaspeech")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("esc-benchmark/wav2vec2-ctc-gigaspeech") model = AutoModelForCTC.from_pretrained("esc-benchmark/wav2vec2-ctc-gigaspeech") - Notebooks
- Google Colab
- Kaggle
| { | |
| "bos_token": "<s>", | |
| "do_lower_case": false, | |
| "eos_token": "</s>", | |
| "name_or_path": "sanchit-gandhi/wav2vec2-ctc-gs-black-box-tokenizer", | |
| "pad_token": "<pad>", | |
| "replace_word_delimiter_char": " ", | |
| "special_tokens_map_file": null, | |
| "tokenizer_class": "Wav2Vec2CTCTokenizer", | |
| "unk_token": "<unk>", | |
| "word_delimiter_token": "|" | |
| } | |