Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 75,
+  "<s>": 74
+}

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": {
+    "72": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": "mal",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,78 @@
+{
+  "mal": {
+    ".": 1,
+    "[PAD]": 73,
+    "[UNK]": 72,
+    "|": 0,
+    "ം": 2,
+    "ഃ": 3,
+    "അ": 4,
+    "ആ": 5,
+    "ഇ": 6,
+    "ഈ": 7,
+    "ഉ": 8,
+    "ഊ": 9,
+    "എ": 10,
+    "ഏ": 11,
+    "ഐ": 12,
+    "ഒ": 13,
+    "ഓ": 14,
+    "ഔ": 15,
+    "ക": 16,
+    "ഖ": 17,
+    "ഗ": 18,
+    "ഘ": 19,
+    "ങ": 20,
+    "ച": 21,
+    "ഛ": 22,
+    "ജ": 23,
+    "ഞ": 24,
+    "ട": 25,
+    "ഠ": 26,
+    "ഡ": 27,
+    "ഢ": 28,
+    "ണ": 29,
+    "ത": 30,
+    "ഥ": 31,
+    "ദ": 32,
+    "ധ": 33,
+    "ന": 34,
+    "പ": 35,
+    "ഫ": 36,
+    "ബ": 37,
+    "ഭ": 38,
+    "മ": 39,
+    "യ": 40,
+    "ര": 41,
+    "റ": 42,
+    "ല": 43,
+    "ള": 44,
+    "ഴ": 45,
+    "വ": 46,
+    "ശ": 47,
+    "ഷ": 48,
+    "സ": 49,
+    "ഹ": 50,
+    "ാ": 51,
+    "ി": 52,
+    "ീ": 53,
+    "ു": 54,
+    "ൂ": 55,
+    "ൃ": 56,
+    "െ": 57,
+    "േ": 58,
+    "ൈ": 59,
+    "ൊ": 60,
+    "ോ": 61,
+    "ൌ": 62,
+    "്": 63,
+    "ൗ": 64,
+    "ൺ": 65,
+    "ൻ": 66,
+    "ർ": 67,
+    "ൽ": 68,
+    "ൾ": 69,
+    "ൿ": 70,
+    "’": 71
+  }
+}