Upload tokenizer

special_tokens_map.json

@@ -1 +1,6 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -1 +1,49 @@
-{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "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",
+  "tokenizer_file": null,
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -1 +1,86 @@
-{"<s>": 1, "<pad>": 0, "</s>": 2, "<unk>": 3, "|": 4, "0": 5, "1": 6, "2": 7, "3": 8, "4": 9, "5": 10, "6": 11, "7": 12, "8": 13, "9": 14, "ँ": 15, "ं": 16, "ः": 17, "अ": 18, "आ": 19, "इ": 20, "ई": 21, "उ": 22, "ऊ": 23, "ऋ": 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, "ल": 57, "व": 58, "श": 59, "ष": 60, "स": 61, "ह": 62, "ा": 63, "ि": 64, "ी": 65, "ु": 66, "ू": 67, "ृ": 68, "ॅ": 69, "े": 70, "ै": 71, "ॉ": 72, "ो": 73, "ौ": 74, "्": 75, "क़": 76, "ख़": 77, "ग़": 78, "ज़": 79, "ड़": 80, "ढ़": 81, "फ़": 82, "य़": 83}
+{
+  "0": 5,
+  "1": 6,
+  "2": 7,
+  "3": 8,
+  "4": 9,
+  "5": 10,
+  "6": 11,
+  "7": 12,
+  "8": 13,
+  "9": 14,
+  "</s>": 2,
+  "<pad>": 0,
+  "<s>": 1,
+  "<unk>": 3,
+  "|": 4,
+  "ँ": 15,
+  "ं": 16,
+  "ः": 17,
+  "अ": 18,
+  "आ": 19,
+  "इ": 20,
+  "ई": 21,
+  "उ": 22,
+  "ऊ": 23,
+  "ऋ": 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,
+  "ल": 57,
+  "व": 58,
+  "श": 59,
+  "ष": 60,
+  "स": 61,
+  "ह": 62,
+  "ा": 63,
+  "ि": 64,
+  "ी": 65,
+  "ु": 66,
+  "ू": 67,
+  "ृ": 68,
+  "ॅ": 69,
+  "े": 70,
+  "ै": 71,
+  "ॉ": 72,
+  "ो": 73,
+  "ौ": 74,
+  "्": 75,
+  "क़": 76,
+  "ख़": 77,
+  "ग़": 78,
+  "ज़": 79,
+  "ड़": 80,
+  "ढ़": 81,
+  "फ़": 82,
+  "य़": 83
+}