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 +1,13 @@
+{
+  "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": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,56 @@
+{
+  "</s>": 2,
+  "<pad>": 0,
+  "<s>": 1,
+  "<unk>": 3,
+  "F": 5,
+  "N": 6,
+  "Q": 7,
+  "a": 8,
+  "aH": 9,
+  "b": 10,
+  "by": 11,
+  "c": 12,
+  "cj": 13,
+  "cy": 14,
+  "d": 15,
+  "e": 16,
+  "eH": 17,
+  "g": 18,
+  "gj": 19,
+  "gw": 20,
+  "gy": 21,
+  "h": 22,
+  "hj": 23,
+  "hy": 24,
+  "i": 25,
+  "iH": 26,
+  "k": 27,
+  "kj": 28,
+  "kw": 29,
+  "ky": 30,
+  "m": 31,
+  "my": 32,
+  "n": 33,
+  "nj": 34,
+  "ny": 35,
+  "o": 36,
+  "oH": 37,
+  "p": 38,
+  "py": 39,
+  "r": 40,
+  "ry": 41,
+  "s": 42,
+  "sj": 43,
+  "sy": 44,
+  "t": 45,
+  "u": 46,
+  "uH": 47,
+  "v": 48,
+  "w": 49,
+  "y": 50,
+  "z": 51,
+  "zj": 52,
+  "zy": 53,
+  "|": 4
+}