Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 38,
+  "<s>": 37
+}

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 +1,47 @@
+{
+  "added_tokens_decoder": {
+    "35": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "pau",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "38": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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 +1,39 @@
+{
+  " ": 20,
+  "I": 27,
+  "N": 11,
+  "U": 0,
+  "[UNK]": 35,
+  "a": 12,
+  "b": 15,
+  "c": 33,
+  "d": 25,
+  "e": 17,
+  "g": 30,
+  "h": 26,
+  "i": 32,
+  "j": 18,
+  "k": 3,
+  "m": 13,
+  "n": 1,
+  "o": 6,
+  "p": 16,
+  "pau": 36,
+  "r": 22,
+  "s": 7,
+  "t": 29,
+  "u": 2,
+  "w": 14,
+  "y": 10,
+  "z": 4,
+  "|": 34,
+  "あ": 28,
+  "い": 24,
+  "か": 21,
+  "こ": 23,
+  "て": 9,
+  "と": 19,
+  "に": 5,
+  "は": 31,
+  "る": 8
+}