Upload tokenizer

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "pau",
+  "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": "pau",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,31 @@
+{
+  "I": 14,
+  "N": 23,
+  "U": 7,
+  "[UNK]": 27,
+  "a": 0,
+  "b": 24,
+  "ch": 9,
+  "d": 22,
+  "e": 5,
+  "g": 25,
+  "h": 13,
+  "i": 17,
+  "j": 11,
+  "k": 1,
+  "m": 12,
+  "n": 21,
+  "o": 18,
+  "p": 15,
+  "pau": 28,
+  "r": 10,
+  "s": 2,
+  "sh": 8,
+  "t": 4,
+  "ts": 6,
+  "u": 19,
+  "w": 3,
+  "y": 16,
+  "z": 20,
+  "|": 26
+}