Upload tokenizer

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 +1,13 @@
+{
+  "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 +1,74 @@
+{
+  "</s>": 2,
+  "<pad>": 1,
+  "<s>": 0,
+  "<unk>": 3,
+  "|": 4,
+  "ം": 5,
+  "ഃ": 6,
+  "അ": 7,
+  "ആ": 8,
+  "ഇ": 9,
+  "ഈ": 10,
+  "ഉ": 11,
+  "ഊ": 12,
+  "ഋ": 13,
+  "എ": 14,
+  "ഏ": 15,
+  "ഐ": 16,
+  "ഒ": 17,
+  "ഓ": 18,
+  "ഔ": 19,
+  "ക": 20,
+  "ഖ": 21,
+  "ഗ": 22,
+  "ഘ": 23,
+  "ങ": 24,
+  "ച": 25,
+  "ഛ": 26,
+  "ജ": 27,
+  "ഞ": 28,
+  "ട": 29,
+  "ഠ": 30,
+  "ഡ": 31,
+  "ഢ": 32,
+  "ണ": 33,
+  "ത": 34,
+  "ഥ": 35,
+  "ദ": 36,
+  "ധ": 37,
+  "ന": 38,
+  "പ": 39,
+  "ഫ": 40,
+  "ബ": 41,
+  "ഭ": 42,
+  "മ": 43,
+  "യ": 44,
+  "ര": 45,
+  "റ": 46,
+  "ല": 47,
+  "ള": 48,
+  "ഴ": 49,
+  "വ": 50,
+  "ശ": 51,
+  "ഷ": 52,
+  "സ": 53,
+  "ഹ": 54,
+  "ാ": 55,
+  "ി": 56,
+  "ീ": 57,
+  "ു": 58,
+  "ൂ": 59,
+  "ൃ": 60,
+  "െ": 61,
+  "േ": 62,
+  "ൈ": 63,
+  "ൊ": 64,
+  "ോ": 65,
+  "്": 66,
+  "ൺ": 67,
+  "ൻ": 68,
+  "ർ": 69,
+  "ൽ": 70,
+  "ൾ": 71
+}