Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 52,
+  "<s>": 51
+}

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 +1,13 @@
+{
+  "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 +1,53 @@
+{
+  "[PAD]": 50,
+  "[UNK]": 49,
+  "|": 0,
+  "ஃ": 1,
+  "அ": 2,
+  "ஆ": 3,
+  "இ": 4,
+  "ஈ": 5,
+  "உ": 6,
+  "ஊ": 7,
+  "எ": 8,
+  "ஏ": 9,
+  "ஐ": 10,
+  "ஒ": 11,
+  "ஓ": 12,
+  "ஔ": 13,
+  "க": 14,
+  "ங": 15,
+  "ச": 16,
+  "ஜ": 17,
+  "ஞ": 18,
+  "ட": 19,
+  "ண": 20,
+  "த": 21,
+  "ந": 22,
+  "ன": 23,
+  "ப": 24,
+  "ம": 25,
+  "ய": 26,
+  "ர": 27,
+  "ற": 28,
+  "ல": 29,
+  "ள": 30,
+  "ழ": 31,
+  "வ": 32,
+  "ஷ": 33,
+  "ஸ": 34,
+  "ஹ": 35,
+  "ா": 36,
+  "ி": 37,
+  "ீ": 38,
+  "ு": 39,
+  "ூ": 40,
+  "ெ": 41,
+  "ே": 42,
+  "ை": 43,
+  "ொ": 44,
+  "ோ": 45,
+  "ௌ": 46,
+  "்": 47,
+  "’": 48
+}