Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 105,
+  "<s>": 104
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "102": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "105": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "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": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,106 @@
+{
+  " ": 0,
+  "!": 1,
+  "\"": 2,
+  "&": 3,
+  "'": 4,
+  ",": 5,
+  "-": 6,
+  ".": 7,
+  ":": 8,
+  ";": 9,
+  "?": 10,
+  "[PAD]": 103,
+  "[UNK]": 102,
+  "|": 11,
+  "ँ": 12,
+  "ं": 13,
+  "ः": 14,
+  "अ": 15,
+  "आ": 16,
+  "इ": 17,
+  "ई": 18,
+  "उ": 19,
+  "ऊ": 20,
+  "ऋ": 21,
+  "ऌ": 22,
+  "ऍ": 23,
+  "ऎ": 24,
+  "ए": 25,
+  "ऐ": 26,
+  "ऑ": 27,
+  "ओ": 28,
+  "औ": 29,
+  "क": 30,
+  "ख": 31,
+  "ग": 32,
+  "घ": 33,
+  "ङ": 34,
+  "च": 35,
+  "छ": 36,
+  "ज": 37,
+  "झ": 38,
+  "ञ": 39,
+  "ट": 40,
+  "ठ": 41,
+  "ड": 42,
+  "ढ": 43,
+  "ण": 44,
+  "त": 45,
+  "थ": 46,
+  "द": 47,
+  "ध": 48,
+  "न": 49,
+  "प": 50,
+  "फ": 51,
+  "ब": 52,
+  "भ": 53,
+  "म": 54,
+  "य": 55,
+  "र": 56,
+  "ऱ": 57,
+  "ल": 58,
+  "ळ": 59,
+  "व": 60,
+  "श": 61,
+  "ष": 62,
+  "स": 63,
+  "ह": 64,
+  "़": 65,
+  "ऽ": 66,
+  "ा": 67,
+  "ि": 68,
+  "ी": 69,
+  "ु": 70,
+  "ू": 71,
+  "ृ": 72,
+  "ॄ": 73,
+  "ॅ": 74,
+  "ॆ": 75,
+  "े": 76,
+  "ै": 77,
+  "ॉ": 78,
+  "ॊ": 79,
+  "ो": 80,
+  "ौ": 81,
+  "्": 82,
+  "॓": 83,
+  "॔": 84,
+  "क़": 85,
+  "ख़": 86,
+  "ग़": 87,
+  "ज़": 88,
+  "ड़": 89,
+  "ढ़": 90,
+  "फ़": 91,
+  "य़": 92,
+  "ॢ": 93,
+  "।": 94,
+  "॥": 95,
+  "ॲ": 96,
+  "–": 97,
+  "‘": 98,
+  "’": 99,
+  "“": 100,
+  "”": 101
+}