add tokenizer

special_tokens_map.json

@@ -1,6 +1 @@
-{
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
-}
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}

tokenizer_config.json

@@ -1,12 +1 @@
-{
-  "bos_token": "<s>",
-  "do_lower_case": false,
-  "eos_token": "</s>",
-  "name_or_path": "jonatasgrosman/wav2vec2-xls-r-1b-english",
-  "pad_token": "<pad>",
-  "replace_word_delimiter_char": " ",
-  "special_tokens_map_file": "/root/.cache/huggingface/transformers/8caa3c129445e09b903b677c369be532669c13e0eeedab0a11dddefe85790904.9d6cd81ef646692fb1c169a880161ea1cb95f49694f220aced9b704b457e51dd",
-  "tokenizer_class": "Wav2Vec2CTCTokenizer",
-  "unk_token": "<unk>",
-  "word_delimiter_token": "|"
-}
+{"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

@@ -1,35 +1 @@
-{
-  "'": 5,
-  "-": 6,
-  "</s>": 2,
-  "<pad>": 0,
-  "<s>": 1,
-  "<unk>": 3,
-  "a": 7,
-  "b": 8,
-  "c": 9,
-  "d": 10,
-  "e": 11,
-  "f": 12,
-  "g": 13,
-  "h": 14,
-  "i": 15,
-  "j": 16,
-  "k": 17,
-  "l": 18,
-  "m": 19,
-  "n": 20,
-  "o": 21,
-  "p": 22,
-  "q": 23,
-  "r": 24,
-  "s": 25,
-  "t": 26,
-  "u": 27,
-  "v": 28,
-  "w": 29,
-  "x": 30,
-  "y": 31,
-  "z": 32,
-  "|": 4
-}
+{"i": 1, "d": 2, "t": 3, "j": 4, "n": 5, "s": 6, "g": 7, "a": 8, "x": 9, "m": 10, "y": 11, "z": 12, "l": 13, "w": 14, "k": 15, "u": 16, "f": 17, "o": 18, "v": 19, "'": 20, "h": 21, "e": 22, "p": 23, "b": 24, "r": 25, "c": 26, "q": 27, "|": 0, "[UNK]": 28, "[PAD]": 29}