Upload tokenizer

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,44 @@
+{
+  "'": 6,
+  "(": 3,
+  ")": 38,
+  "*": 2,
+  "[PAD]": 41,
+  "[UNK]": 40,
+  "`": 29,
+  "a": 21,
+  "b": 25,
+  "c": 20,
+  "d": 28,
+  "e": 15,
+  "f": 13,
+  "g": 27,
+  "h": 17,
+  "i": 35,
+  "j": 26,
+  "k": 1,
+  "l": 37,
+  "m": 12,
+  "n": 4,
+  "o": 36,
+  "p": 33,
+  "q": 32,
+  "r": 31,
+  "s": 5,
+  "t": 30,
+  "u": 19,
+  "v": 10,
+  "w": 7,
+  "x": 23,
+  "y": 11,
+  "z": 24,
+  "|": 16,
+  "á": 9,
+  "ã": 39,
+  "é": 0,
+  "ó": 14,
+  "ː": 8,
+  "‘": 18,
+  "’": 22,
+  "•": 34
+}