Commit
•
0dcd8f4
1
Parent(s):
d8f0a7a
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 |
+
{"ँ": 1, "ं": 2, "ः": 3, "अ": 4, "आ": 5, "इ": 6, "ई": 7, "उ": 8, "ऊ": 9, "ऋ": 10, "ए": 11, "ऐ": 12, "ऑ": 13, "ओ": 14, "औ": 15, "क": 16, "ख": 17, "ग": 18, "घ": 19, "च": 20, "छ": 21, "ज": 22, "झ": 23, "ञ": 24, "ट": 25, "ठ": 26, "ड": 27, "ढ": 28, "ण": 29, "त": 30, "थ": 31, "द": 32, "ध": 33, "न": 34, "प": 35, "फ": 36, "ब": 37, "भ": 38, "म": 39, "य": 40, "र": 41, "ल": 42, "व": 43, "श": 44, "ष": 45, "स": 46, "ह": 47, "़": 48, "ा": 49, "ि": 50, "ी": 51, "ु": 52, "ू": 53, "ृ": 54, "ॅ": 55, "े": 56, "ै": 57, "ॉ": 58, "ो": 59, "ौ": 60, "्": 61, "क़": 62, "ग़": 63, "ज़": 64, "ड़": 65, "ढ़": 66, "|": 0, "[UNK]": 67, "[PAD]": 68}
|