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 +1,65 @@
+{
+  "[PAD]": 62,
+  "[UNK]": 61,
+  "aa": 40,
+  "ae": 55,
+  "ah": 19,
+  "ao": 31,
+  "aw": 37,
+  "ax": 60,
+  "ax-h": 25,
+  "axr": 52,
+  "ay": 32,
+  "b": 54,
+  "bcl": 26,
+  "ch": 21,
+  "d": 45,
+  "dcl": 51,
+  "dh": 47,
+  "dx": 17,
+  "eh": 44,
+  "el": 14,
+  "em": 48,
+  "en": 33,
+  "eng": 58,
+  "epi": 30,
+  "er": 24,
+  "ey": 29,
+  "f": 20,
+  "g": 28,
+  "gcl": 39,
+  "h#": 0,
+  "hh": 3,
+  "hv": 34,
+  "ih": 59,
+  "ix": 57,
+  "iy": 41,
+  "jh": 2,
+  "k": 23,
+  "kcl": 13,
+  "l": 43,
+  "m": 35,
+  "n": 50,
+  "ng": 8,
+  "nx": 16,
+  "ow": 46,
+  "oy": 53,
+  "p": 49,
+  "pau": 56,
+  "pcl": 7,
+  "q": 38,
+  "r": 1,
+  "s": 5,
+  "sh": 9,
+  "t": 27,
+  "tcl": 22,
+  "th": 36,
+  "uh": 42,
+  "uw": 10,
+  "ux": 15,
+  "v": 11,
+  "w": 18,
+  "y": 6,
+  "z": 4,
+  "zh": 12
+}