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 @@
+{"ਿ": 0, "ਦ": 1, "ਯ": 2, "ੰ": 3, "ਾ": 4, "ਸ਼": 5, "ਉ": 6, "ਵ": 7, "ਡ": 8, "ਜ਼": 9, "ਥ": 10, "ਗ਼": 11, "ਭ": 12, "ਊ": 13, "ਆ": 14, "ਸ": 15, "ਬ": 16, "ੱ": 17, "਼": 18, "੍": 19, "ਝ": 20, "ਜ": 21, "ੋ": 22, "ਰ": 23, "ਐ": 24, "ਗ": 25, "ਟ": 26, "ਫ": 27, "ਈ": 28, "ੀ": 29, "ਮ": 30, "ੇ": 31, "ੁ": 32, "ਘ": 33, "ਅ": 34, "ਖ": 35, "ਪ": 36, "ਲ਼": 37, "¤": 38, "ਹ": 39, "ਇ": 40, "ੌ": 41, "ਲ": 42, "ਔ": 43, "ਧ": 44, "ਂ": 45, "ਤ": 46, "ਚ": 47, "ਓ": 48, "ਖ਼": 49, "ਠ": 50, "ਕ": 51, "ਛ": 52, "ਨ": 53, "ਢ": 54, "ੈ": 55, "ਣ": 56, " ": 57, "ਏ": 58, "ਫ਼": 59, "ੂ": 60, "’": 61, "ੜ": 62, "[UNK]": 63, "[PAD]": 64}