Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 74,
+  "<s>": 73
+}

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

vocab.json

@@ -0,0 +1,75 @@
+{
+  "[PAD]": 72,
+  "[UNK]": 71,
+  "a": 1,
+  "e": 2,
+  "f": 3,
+  "i": 4,
+  "l": 5,
+  "m": 6,
+  "p": 7,
+  "r": 8,
+  "u": 9,
+  "w": 10,
+  "|": 0,
+  "ँ": 11,
+  "ं": 12,
+  "ः": 13,
+  "अ": 14,
+  "आ": 15,
+  "इ": 16,
+  "ई": 17,
+  "उ": 18,
+  "ऊ": 19,
+  "ए": 20,
+  "ऐ": 21,
+  "ऑ": 22,
+  "ओ": 23,
+  "औ": 24,
+  "क": 25,
+  "ख": 26,
+  "ग": 27,
+  "घ": 28,
+  "च": 29,
+  "छ": 30,
+  "ज": 31,
+  "झ": 32,
+  "ट": 33,
+  "ठ": 34,
+  "ड": 35,
+  "ढ": 36,
+  "ण": 37,
+  "त": 38,
+  "थ": 39,
+  "द": 40,
+  "ध": 41,
+  "न": 42,
+  "प": 43,
+  "फ": 44,
+  "ब": 45,
+  "भ": 46,
+  "म": 47,
+  "य": 48,
+  "र": 49,
+  "ल": 50,
+  "व": 51,
+  "श": 52,
+  "ष": 53,
+  "स": 54,
+  "ह": 55,
+  "़": 56,
+  "ा": 57,
+  "ि": 58,
+  "ी": 59,
+  "ु": 60,
+  "ू": 61,
+  "ृ": 62,
+  "े": 63,
+  "ै": 64,
+  "ॉ": 65,
+  "ो": 66,
+  "ौ": 67,
+  "्": 68,
+  "ड़": 69,
+  "।": 70
+}