Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 50,
+  "<s>": 49
+}

special_tokens_map.json

@@ -0,0 +1,22 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "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": "nan",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,54 @@
+{
+  "nan": {
+    "[PAD]": 49,
+    "[UNK]": 48,
+    "a": 1,
+    "b": 2,
+    "c": 3,
+    "e": 4,
+    "g": 5,
+    "h": 6,
+    "i": 7,
+    "j": 8,
+    "k": 9,
+    "l": 10,
+    "m": 11,
+    "n": 12,
+    "o": 13,
+    "p": 14,
+    "r": 15,
+    "s": 16,
+    "t": 17,
+    "u": 18,
+    "y": 19,
+    "|": 0,
+    "à": 21,
+    "á": 22,
+    "è": 23,
+    "é": 24,
+    "ê": 25,
+    "ì": 26,
+    "í": 27,
+    "ò": 28,
+    "ó": 29,
+    "ù": 30,
+    "ú": 31,
+    "ā": 32,
+    "ē": 33,
+    "ī": 34,
+    "ı": 35,
+    "ń": 36,
+    "ō": 37,
+    "ū": 38,
+    "ǎ": 39,
+    "ǹ": 40,
+    "́": 41,
+    "̂": 42,
+    "̄": 43,
+    "̍": 44,
+    "͘": 45,
+    "ḿ": 46,
+    "ⁿ": 47,
+    "⿸": 48
+  }
+}