| { |
| "tokenizer_class": "Wav2Vec2CTCTokenizer", |
| "processor_class": "Wav2Vec2Processor", |
| "vocab": { |
| "</s>": 2, |
| "<pad>": 0, |
| "<s>": 1, |
| "<unk>": 3, |
| "a": 4, |
| "b": 5, |
| "d": 6, |
| "e": 7, |
| "f": 8, |
| "h": 9, |
| "i": 10, |
| "j": 11, |
| "k": 12, |
| "l": 13, |
| "m": 14, |
| "n": 15, |
| "o": 16, |
| "p": 17, |
| "s": 18, |
| "t": 19, |
| "u": 20, |
| "v": 21, |
| "w": 22, |
| "z": 23, |
| "æ": 24, |
| "ð": 25, |
| "ŋ": 26, |
| "ɑ": 27, |
| "ɔ": 28, |
| "ə": 29, |
| "ɛ": 30, |
| "ɡ": 31, |
| "ɪ": 32, |
| "ɹ": 33, |
| "ɾ": 34, |
| "ʃ": 35, |
| "ʊ": 36, |
| "ʌ": 37, |
| "ʒ": 38, |
| "ʔ": 39, |
| "θ": 40 |
| }, |
| "added_tokens_decoder": { |
| "0": { |
| "content": "<pad>", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "1": { |
| "content": "<s>", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "2": { |
| "content": "</s>", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "3": { |
| "content": "<unk>", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| } |
| }, |
| "special_tokens_map": { |
| "bos_token": "<s>", |
| "eos_token": "</s>", |
| "pad_token": "<pad>", |
| "unk_token": "<unk>" |
| }, |
| "bos_token": "<s>", |
| "eos_token": "</s>", |
| "unk_token": "<unk>", |
| "pad_token": "<pad>", |
| "word_delimiter_token": "|", |
| "clean_up_tokenization_spaces": false, |
| "do_lower_case": false, |
| "model_max_length": 1000000000000000019884624838656 |
| } |
|
|
