add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 52, "</s>": 53}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"ூ": 0, "ே": 1, "ு": 2, "ஊ": 3, "ர": 4, "ந": 5, "ஸ": 6, "ஷ": 7, "ப": 8, "ெ": 9, "ஔ": 10, "ஈ": 11, "ஐ": 12, "வ": 14, "’": 15, "ற": 16, "அ": 17, "ை": 18, "க": 19, "ட": 20, "ம": 21, "்": 22, "ய": 23, "ோ": 24, "ஒ": 25, "எ": 26, "ள": 27, "த": 28, "உ": 29, "ல": 30, "ி": 31, "ஜ": 32, "ஞ": 33, "ா": 34, "ச": 35, "ஓ": 36, "ங": 37, "ீ": 38, "ஹ": 39, "ழ": 40, "இ": 41, "ஏ": 42, "ௌ": 43, "ொ": 44, "'": 45, "ஆ": 46, "ண": 47, "ன": 48, "ஃ": 49, "|": 13, "[UNK]": 50, "[PAD]": 51}