Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 142,
+  "<s>": 141
+}

special_tokens_map.json

@@ -0,0 +1,36 @@
+{
+  "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
+    },
+    {
+      "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": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": " "
+}

vocab.json

@@ -0,0 +1,143 @@
+{
+  " ": 0,
+  "#": 1,
+  "$": 2,
+  "*": 3,
+  "+": 4,
+  "/": 5,
+  "0": 6,
+  "1": 7,
+  "2": 8,
+  "3": 9,
+  "4": 10,
+  "5": 11,
+  "6": 12,
+  "7": 13,
+  "8": 14,
+  "9": 15,
+  "<": 16,
+  "=": 17,
+  ">": 18,
+  "@": 19,
+  "[PAD]": 140,
+  "[UNK]": 139,
+  "\\": 20,
+  "^": 21,
+  "a": 22,
+  "b": 23,
+  "c": 24,
+  "d": 25,
+  "e": 26,
+  "f": 27,
+  "g": 28,
+  "h": 29,
+  "i": 30,
+  "j": 31,
+  "k": 32,
+  "l": 33,
+  "m": 34,
+  "n": 35,
+  "o": 36,
+  "p": 37,
+  "q": 38,
+  "r": 39,
+  "s": 40,
+  "t": 41,
+  "u": 42,
+  "v": 43,
+  "w": 44,
+  "x": 45,
+  "y": 46,
+  "z": 47,
+  "{": 48,
+  "}": 49,
+  "~": 50,
+  "°": 51,
+  "º": 52,
+  "×": 53,
+  "λ": 54,
+  "μ": 55,
+  "π": 56,
+  "φ": 57,
+  "ω": 58,
+  "ँ": 59,
+  "ं": 60,
+  "ः": 61,
+  "अ": 62,
+  "आ": 63,
+  "इ": 64,
+  "ई": 65,
+  "उ": 66,
+  "ऊ": 67,
+  "ऋ": 68,
+  "ऍ": 69,
+  "ए": 70,
+  "ऐ": 71,
+  "ऑ": 72,
+  "ओ": 73,
+  "औ": 74,
+  "क": 75,
+  "ख": 76,
+  "ग": 77,
+  "घ": 78,
+  "च": 79,
+  "छ": 80,
+  "ज": 81,
+  "झ": 82,
+  "ञ": 83,
+  "ट": 84,
+  "ठ": 85,
+  "ड": 86,
+  "ढ": 87,
+  "ण": 88,
+  "त": 89,
+  "थ": 90,
+  "द": 91,
+  "ध": 92,
+  "न": 93,
+  "ऩ": 94,
+  "प": 95,
+  "फ": 96,
+  "ब": 97,
+  "भ": 98,
+  "म": 99,
+  "य": 100,
+  "र": 101,
+  "ऱ": 102,
+  "ल": 103,
+  "व": 104,
+  "श": 105,
+  "ष": 106,
+  "स": 107,
+  "ह": 108,
+  "़": 109,
+  "ा": 110,
+  "ि": 111,
+  "ी": 112,
+  "ु": 113,
+  "ू": 114,
+  "ृ": 115,
+  "ॅ": 116,
+  "े": 117,
+  "ै": 118,
+  "ॉ": 119,
+  "ो": 120,
+  "ौ": 121,
+  "्": 122,
+  "०": 123,
+  "१": 124,
+  "२": 125,
+  "३": 126,
+  "४": 127,
+  "५": 128,
+  "६": 129,
+  "७": 130,
+  "८": 131,
+  "९": 132,
+  "•": 133,
+  "…": 134,
+  "›": 135,
+  "⅓": 136,
+  "→": 137,
+  "−": 138
+}