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 +1,17 @@
+{
+  "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": " ",
+  "reserved_token1": "?reserved2?",
+  "reserved_token2": "?reserved3?",
+  "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 @@
+{
+  "<pad>": 23,
+  "<sil>": 31,
+  "<spn>": 43,
+  "<unk>": 11,
+  "?reserved2?": 19,
+  "?reserved3?": 14,
+  "AA": 24,
+  "AE": 6,
+  "AH": 32,
+  "AO": 3,
+  "AW": 44,
+  "AY": 5,
+  "B": 2,
+  "CH": 33,
+  "D": 12,
+  "DH": 20,
+  "DX": 26,
+  "EH": 40,
+  "ER": 15,
+  "EY": 27,
+  "F": 41,
+  "G": 0,
+  "HH": 18,
+  "IH": 34,
+  "IY": 1,
+  "JH": 29,
+  "K": 25,
+  "L": 16,
+  "M": 17,
+  "N": 45,
+  "NG": 35,
+  "OW": 36,
+  "OY": 28,
+  "P": 39,
+  "R": 13,
+  "S": 4,
+  "SH": 8,
+  "T": 7,
+  "TH": 42,
+  "UH": 21,
+  "UW": 10,
+  "V": 37,
+  "W": 30,
+  "Y": 22,
+  "Z": 9,
+  "ZH": 38
+}