Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 83,
+  "<s>": 82
+}

special_tokens_map.json

@@ -0,0 +1,22 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "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": " ",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,84 @@
+{
+  "!": 1,
+  "'": 2,
+  ",": 3,
+  "-": 4,
+  ".": 5,
+  ":": 6,
+  ";": 7,
+  "[PAD]": 81,
+  "[UNK]": 80,
+  "|": 0,
+  "ം": 8,
+  "ഃ": 9,
+  "അ": 10,
+  "ആ": 11,
+  "ഇ": 12,
+  "ഈ": 13,
+  "ഉ": 14,
+  "ഊ": 15,
+  "ഋ": 16,
+  "എ": 17,
+  "ഏ": 18,
+  "ഐ": 19,
+  "ഒ": 20,
+  "ഓ": 21,
+  "ഔ": 22,
+  "ക": 23,
+  "ഖ": 24,
+  "ഗ": 25,
+  "ഘ": 26,
+  "ങ": 27,
+  "ച": 28,
+  "ഛ": 29,
+  "ജ": 30,
+  "ഝ": 31,
+  "ഞ": 32,
+  "ട": 33,
+  "ഠ": 34,
+  "ഡ": 35,
+  "ഢ": 36,
+  "ണ": 37,
+  "ത": 38,
+  "ഥ": 39,
+  "ദ": 40,
+  "ധ": 41,
+  "ന": 42,
+  "പ": 43,
+  "ഫ": 44,
+  "ബ": 45,
+  "ഭ": 46,
+  "മ": 47,
+  "യ": 48,
+  "ര": 49,
+  "റ": 50,
+  "ല": 51,
+  "ള": 52,
+  "ഴ": 53,
+  "വ": 54,
+  "ശ": 55,
+  "ഷ": 56,
+  "സ": 57,
+  "ഹ": 58,
+  "ാ": 59,
+  "ി": 60,
+  "ീ": 61,
+  "ു": 62,
+  "ൂ": 63,
+  "ൃ": 64,
+  "െ": 65,
+  "േ": 66,
+  "ൈ": 67,
+  "ൊ": 68,
+  "ോ": 69,
+  "ൌ": 70,
+  "്": 71,
+  "ൗ": 72,
+  "ൺ": 73,
+  "ൻ": 74,
+  "ർ": 75,
+  "ൽ": 76,
+  "ൾ": 77,
+  "‌": 78,
+  "‍": 79
+}