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": "<s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "<pad>",
+      "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 +1,69 @@
-{"<s>": 0, "<pad>": 1, "</s>": 2, "<unk>": 3, "|":4, "ँ": 5, "ं": 6, "ः": 7, "अ": 8, "आ": 9, "इ": 10, "ई": 11, "उ": 12, "ऊ": 13, "ऋ": 14, "ए": 15, "ऐ": 16, "ऑ": 17, "ओ": 18, "औ": 19, "क": 20, "ख": 21, "ग": 22, "घ": 23, "ङ": 24, "च": 25, "छ": 26, "ज": 27, "झ": 28, "ञ": 29, "ट": 30, "ठ": 31, "ड": 32, "ढ": 33, "ण": 34, "त": 35, "थ": 36, "द": 37, "ध": 38, "न": 39, "प": 40, "फ": 41, "ब": 42, "भ": 43, "म": 44, "य": 45, "र": 46, "ल": 47, "व": 48, "श": 49, "ष": 50, "स": 51, "ह": 52, "़": 53, "ा": 54, "ि": 55, "ी": 56, "ु": 57, "ू": 58, "ृ": 59, "ॅ": 60, "े": 61, "ै": 62, "ॉ": 63, "ो": 64, "ौ": 65, "्": 66}
+{
+  "</s>": 2,
+  "<pad>": 1,
+  "<s>": 0,
+  "<unk>": 3,
+  "|": 4,
+  "ँ": 5,
+  "ं": 6,
+  "ः": 7,
+  "अ": 8,
+  "आ": 9,
+  "इ": 10,
+  "ई": 11,
+  "उ": 12,
+  "ऊ": 13,
+  "ऋ": 14,
+  "ए": 15,
+  "ऐ": 16,
+  "ऑ": 17,
+  "ओ": 18,
+  "औ": 19,
+  "क": 20,
+  "ख": 21,
+  "ग": 22,
+  "घ": 23,
+  "ङ": 24,
+  "च": 25,
+  "छ": 26,
+  "ज": 27,
+  "झ": 28,
+  "ञ": 29,
+  "ट": 30,
+  "ठ": 31,
+  "ड": 32,
+  "ढ": 33,
+  "ण": 34,
+  "त": 35,
+  "थ": 36,
+  "द": 37,
+  "ध": 38,
+  "न": 39,
+  "प": 40,
+  "फ": 41,
+  "ब": 42,
+  "भ": 43,
+  "म": 44,
+  "य": 45,
+  "र": 46,
+  "ल": 47,
+  "व": 48,
+  "श": 49,
+  "ष": 50,
+  "स": 51,
+  "ह": 52,
+  "़": 53,
+  "ा": 54,
+  "ि": 55,
+  "ी": 56,
+  "ु": 57,
+  "ू": 58,
+  "ृ": 59,
+  "ॅ": 60,
+  "े": 61,
+  "ै": 62,
+  "ॉ": 63,
+  "ो": 64,
+  "ौ": 65,
+  "्": 66
+}