Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 82,
+  "<s>": 81
+}

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 +1,12 @@
+{
+  "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": " ",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,83 @@
+{
+  "/": 1,
+  "0": 2,
+  "1": 3,
+  "2": 4,
+  "3": 5,
+  "4": 6,
+  "5": 7,
+  "6": 8,
+  "7": 9,
+  "8": 10,
+  "9": 11,
+  "[": 12,
+  "[PAD]": 80,
+  "[UNK]": 79,
+  "]": 13,
+  "_": 14,
+  "a": 15,
+  "b": 16,
+  "c": 17,
+  "d": 18,
+  "e": 19,
+  "f": 20,
+  "g": 21,
+  "h": 22,
+  "i": 23,
+  "j": 24,
+  "k": 25,
+  "l": 26,
+  "m": 27,
+  "n": 28,
+  "o": 29,
+  "p": 30,
+  "q": 31,
+  "r": 32,
+  "s": 33,
+  "t": 34,
+  "u": 35,
+  "v": 36,
+  "w": 37,
+  "x": 38,
+  "y": 39,
+  "z": 40,
+  "|": 0,
+  "~": 41,
+  "£": 42,
+  "¥": 43,
+  "°": 44,
+  "²": 45,
+  "½": 46,
+  "¾": 47,
+  "à": 48,
+  "á": 49,
+  "ã": 50,
+  "ç": 51,
+  "è": 52,
+  "é": 53,
+  "ì": 54,
+  "í": 55,
+  "ñ": 56,
+  "ò": 57,
+  "ó": 58,
+  "õ": 59,
+  "ù": 60,
+  "ú": 61,
+  "ü": 62,
+  "ă": 63,
+  "ē": 64,
+  "ī": 65,
+  "ł": 66,
+  "ū": 67,
+  "ǹ": 68,
+  "ș": 69,
+  "̀": 70,
+  "̄": 71,
+  "ṅ": 72,
+  "ị": 73,
+  "ọ": 74,
+  "ụ": 75,
+  "–": 76,
+  "—": 77,
+  "‘": 78
+}