add tokenizer

special_tokens_map.json

@@ -1 +1 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "special_tokens_map_file": "/root/.cache/huggingface/transformers/5323197ecff8736fa0fb39ba935d69053e8cee16c85dbd3d1bee8ec02fbd585a.a21d51735cf8667bcd610f057e88548d5d6a381401f6b4501a8bc6c1a9dc8498", "name_or_path": "BakhtUllah123/XLS-R_53_english", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2ProcessorWithLM"}
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -1 +1 @@
-{"w": 0, "z": 1, "o": 2, "t": 3, "k": 4, "g": 5, "b": 6, "c": 7, "d": 8, "m": 10, "i": 11, "q": 12, "l": 13, "u": 14, "'": 15, "x": 16, "s": 17, "j": 18, "v": 19, "h": 20, "e": 21, "f": 22, "a": 23, "y": 24, "p": 25, "r": 26, "n": 27, "|": 9, "[UNK]": 28, "[PAD]": 29}
+{"r": 0, "k": 1, "s": 2, "d": 3, "c": 4, "f": 5, "w": 6, "n": 7, "m": 8, "y": 9, "l": 10, "p": 12, "u": 13, "o": 14, "'": 15, "i": 16, "t": 17, "e": 18, "v": 19, "j": 20, "h": 21, "z": 22, "g": 23, "a": 24, "x": 25, "q": 26, "b": 27, "|": 11, "[UNK]": 28, "[PAD]": 29}