| { |
| "added_tokens_decoder": { |
| "6": { |
| "content": "by", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "7": { |
| "content": "ch", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "8": { |
| "content": "cl", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "10": { |
| "content": "dy", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "14": { |
| "content": "gy", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "16": { |
| "content": "hy", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "20": { |
| "content": "ky", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "22": { |
| "content": "my", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "24": { |
| "content": "ny", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "27": { |
| "content": "py", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "29": { |
| "content": "ry", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "31": { |
| "content": "sh", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "33": { |
| "content": "ts", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "34": { |
| "content": "ty", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "40": { |
| "content": "[UNK]", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "41": { |
| "content": "[PAD]", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": true, |
| "single_word": false, |
| "special": false |
| }, |
| "42": { |
| "content": "<s>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "43": { |
| "content": "</s>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| } |
| }, |
| "bos_token": "<s>", |
| "clean_up_tokenization_spaces": false, |
| "do_lower_case": false, |
| "eos_token": "</s>", |
| "extra_special_tokens": {}, |
| "model_max_length": 1000000000000000019884624838656, |
| "pad_token": "[PAD]", |
| "processor_class": "Wav2Vec2Processor", |
| "replace_word_delimiter_char": " ", |
| "target_lang": null, |
| "tokenizer_class": "Wav2Vec2CTCTokenizer", |
| "unk_token": "[UNK]", |
| "word_delimiter_token": "|" |
| } |
|
|
