Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 70,
+  "<s>": 69
+}

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 +1,47 @@
+{
+  "added_tokens_decoder": {
+    "67": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "70": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "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]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": "muw",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,73 @@
+{
+  "muw": {
+    "(": 1,
+    ")": 2,
+    ",": 3,
+    "-": 4,
+    ":": 5,
+    "?": 6,
+    "[PAD]": 68,
+    "[UNK]": 67,
+    "|": 0,
+    "ं": 7,
+    "ः": 8,
+    "अ": 9,
+    "आ": 10,
+    "इ": 11,
+    "ई": 12,
+    "उ": 13,
+    "ऊ": 14,
+    "ए": 15,
+    "ऑ": 16,
+    "ओ": 17,
+    "क": 18,
+    "ख": 19,
+    "ग": 20,
+    "घ": 21,
+    "ङ": 22,
+    "च": 23,
+    "छ": 24,
+    "ज": 25,
+    "झ": 26,
+    "ञ": 27,
+    "ट": 28,
+    "ठ": 29,
+    "ड": 30,
+    "ण": 31,
+    "त": 32,
+    "थ": 33,
+    "द": 34,
+    "ध": 35,
+    "न": 36,
+    "प": 37,
+    "फ": 38,
+    "ब": 39,
+    "भ": 40,
+    "म": 41,
+    "य": 42,
+    "र": 43,
+    "ल": 44,
+    "व": 45,
+    "श": 46,
+    "ष": 47,
+    "स": 48,
+    "ह": 49,
+    "़": 50,
+    "ा": 51,
+    "ि": 52,
+    "ी": 53,
+    "ु": 54,
+    "ू": 55,
+    "ृ": 56,
+    "े": 57,
+    "ै": 58,
+    "ॉ": 59,
+    "ो": 60,
+    "ौ": 61,
+    "्": 62,
+    "ड़": 63,
+    "ढ़": 64,
+    "।": 65,
+    "‌": 66
+  }
+}