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