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 +1,16 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "other_special_token": "<???>",
+  "pad_token": "<PAD>",
+  "replace_word_delimiter_char": " ",
+  "silence_token": "<SIL>",
+  "spoken_noise_token": "<SPN>",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "<UNK>",
+  "vocab_size": 46,
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,48 @@
+{
+  "<???>": 24,
+  "<PAD>": 3,
+  "<SIL>": 2,
+  "<SPN>": 18,
+  "<UNK>": 19,
+  "AA": 1,
+  "AE": 8,
+  "AH": 6,
+  "AO": 36,
+  "AW": 33,
+  "AY": 17,
+  "B": 20,
+  "CH": 43,
+  "D": 35,
+  "DH": 42,
+  "DX": 10,
+  "EH": 7,
+  "ER": 12,
+  "EY": 44,
+  "F": 27,
+  "G": 40,
+  "HH": 9,
+  "IH": 41,
+  "IY": 14,
+  "JH": 28,
+  "K": 21,
+  "L": 22,
+  "M": 37,
+  "N": 0,
+  "NG": 25,
+  "OW": 16,
+  "OY": 15,
+  "P": 32,
+  "R": 45,
+  "S": 38,
+  "SH": 29,
+  "T": 5,
+  "TH": 31,
+  "UH": 11,
+  "UW": 4,
+  "V": 34,
+  "W": 30,
+  "Y": 39,
+  "Z": 13,
+  "ZH": 26,
+  "|": 23
+}