add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 68, "</s>": 69}

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 @@
+{"ං": 1, "අ": 2, "ආ": 3, "ඇ": 4, "ඈ": 5, "ඉ": 6, "ඊ": 7, "උ": 8, "ඌ": 9, "එ": 10, "ඒ": 11, "ඓ": 12, "ඔ": 13, "ඕ": 14, "ක": 15, "ඛ": 16, "ග": 17, "ඝ": 18, "ඟ": 19, "ච": 20, "ඡ": 21, "ජ": 22, "ඤ": 23, "ට": 24, "ඨ": 25, "ඩ": 26, "ඪ": 27, "ණ": 28, "ඬ": 29, "ත": 30, "ථ": 31, "ද": 32, "ධ": 33, "න": 34, "ඳ": 35, "ප": 36, "ඵ": 37, "බ": 38, "භ": 39, "ම": 40, "ඹ": 41, "ය": 42, "ර": 43, "ල": 44, "ව": 45, "ශ": 46, "ෂ": 47, "ස": 48, "හ": 49, "ළ": 50, "ෆ": 51, "්": 52, "ා": 53, "ැ": 54, "ෑ": 55, "ි": 56, "ී": 57, "ු": 58, "ූ": 59, "ෙ": 60, "ේ": 61, "ෛ": 62, "ො": 63, "ෝ": 64, "ෞ": 65, "|": 0, "[UNK]": 66, "[PAD]": 67}