Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 177,
+  "<s>": 176
+}

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": "npi",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,181 @@
+{
+  "npi": {
+    "\n": 0,
+    "!": 2,
+    "\"": 3,
+    "#": 4,
+    "$": 5,
+    "%": 6,
+    "&": 7,
+    "'": 8,
+    "(": 9,
+    ")": 10,
+    "+": 11,
+    ",": 12,
+    "-": 13,
+    ".": 14,
+    "/": 15,
+    "0": 16,
+    "1": 17,
+    "2": 18,
+    "3": 19,
+    "4": 20,
+    "5": 21,
+    "6": 22,
+    "7": 23,
+    "8": 24,
+    "9": 25,
+    ":": 26,
+    ";": 27,
+    "=": 28,
+    "?": 29,
+    "A": 30,
+    "B": 31,
+    "C": 32,
+    "D": 33,
+    "E": 34,
+    "F": 35,
+    "G": 36,
+    "H": 37,
+    "I": 38,
+    "J": 39,
+    "K": 40,
+    "L": 41,
+    "M": 42,
+    "N": 43,
+    "O": 44,
+    "P": 45,
+    "Q": 46,
+    "R": 47,
+    "S": 48,
+    "T": 49,
+    "U": 50,
+    "V": 51,
+    "W": 52,
+    "Y": 53,
+    "Z": 54,
+    "[": 55,
+    "[PAD]": 176,
+    "[UNK]": 175,
+    "]": 56,
+    "_": 57,
+    "`": 58,
+    "a": 59,
+    "b": 60,
+    "c": 61,
+    "d": 62,
+    "e": 63,
+    "f": 64,
+    "g": 65,
+    "h": 66,
+    "i": 67,
+    "j": 68,
+    "k": 69,
+    "l": 70,
+    "m": 71,
+    "n": 72,
+    "o": 73,
+    "p": 74,
+    "q": 75,
+    "r": 76,
+    "s": 77,
+    "t": 78,
+    "u": 79,
+    "v": 80,
+    "w": 81,
+    "x": 82,
+    "y": 83,
+    "z": 84,
+    "|": 1,
+    "¥": 86,
+    "«": 87,
+    "®": 88,
+    "·": 89,
+    "Ï": 90,
+    "è": 91,
+    "é": 92,
+    "÷": 93,
+    "ँ": 94,
+    "ं": 95,
+    "ः": 96,
+    "अ": 97,
+    "आ": 98,
+    "इ": 99,
+    "ई": 100,
+    "उ": 101,
+    "ऊ": 102,
+    "ऋ": 103,
+    "ए": 104,
+    "ऐ": 105,
+    "ओ": 106,
+    "औ": 107,
+    "क": 108,
+    "ख": 109,
+    "ग": 110,
+    "घ": 111,
+    "ङ": 112,
+    "च": 113,
+    "छ": 114,
+    "ज": 115,
+    "झ": 116,
+    "ञ": 117,
+    "ट": 118,
+    "ठ": 119,
+    "ड": 120,
+    "ढ": 121,
+    "ण": 122,
+    "त": 123,
+    "थ": 124,
+    "द": 125,
+    "ध": 126,
+    "न": 127,
+    "प": 128,
+    "फ": 129,
+    "ब": 130,
+    "भ": 131,
+    "म": 132,
+    "य": 133,
+    "र": 134,
+    "ल": 135,
+    "व": 136,
+    "श": 137,
+    "ष": 138,
+    "स": 139,
+    "ह": 140,
+    "़": 141,
+    "ा": 142,
+    "ि": 143,
+    "ी": 144,
+    "ु": 145,
+    "ू": 146,
+    "ृ": 147,
+    "े": 148,
+    "ै": 149,
+    "ो": 150,
+    "ौ": 151,
+    "्": 152,
+    "ॐ": 153,
+    "।": 154,
+    "०": 155,
+    "१": 156,
+    "२": 157,
+    "३": 158,
+    "४": 159,
+    "५": 160,
+    "६": 161,
+    "७": 162,
+    "८": 163,
+    "९": 164,
+    "​": 165,
+    "‌": 166,
+    "‍": 167,
+    "–": 168,
+    "—": 169,
+    "‘": 170,
+    "’": 171,
+    "“": 172,
+    "”": 173,
+    "…": 174,
+    " ": 175
+  }
+}