add tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +1 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 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
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"": 0, "রেখেছেন": 1, "বাজুসের": 2, "বল": 3, "চানাচুরটা": 4, "কেজি": 5, "ডানের": 6, "৫": 7, "ল্যাপটপটা": 8, "মোবাইলটা": 9, "দেন": 10, "জন্য": 11, "কেমন": 12, "দাম": 14, "টা": 15, "হ্যালো": 16, "চেয়ারটা": 17, "আলু": 18, "কি": 19, "কত": 20, "এসেছে": 21, "শ্যাম্পুর": 22, "কোথায়": 23, "কলম": 24, "বাসার": 25, "ম্যাম": 26, "বালতিটার": 27, "প্রাইজ": 28, "আছে": 29, "|": 13, "[UNK]": 30, "[PAD]": 31}
|