add tokenizer

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}

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": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

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