tokenizer_config.json
| 1 | { |
| 2 | "bos_token": "<s>", |
| 3 | "clean_up_tokenization_spaces": true, |
| 4 | "do_lower_case": false, |
| 5 | "eos_token": "</s>", |
| 6 | "model_max_length": 1000000000000000019884624838656, |
| 7 | "pad_token": "<pad>", |
| 8 | "processor_class": "Wav2Vec2Processor", |
| 9 | "replace_word_delimiter_char": " ", |
| 10 | "target_lang": "eng", |
| 11 | "tokenizer_class": "Wav2Vec2CTCTokenizer", |
| 12 | "unk_token": "<unk>", |
| 13 | "word_delimiter_token": "|" |
| 14 | } |
| 15 | |