add tokenizer
Browse files- special_tokens_map.json +6 -0
- tokenizer_config.json +10 -0
- vocab.json +75 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"unk_token": "[UNK]"
|
| 6 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"do_lower_case": false,
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"pad_token": "[PAD]",
|
| 6 |
+
"replace_word_delimiter_char": " ",
|
| 7 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 8 |
+
"unk_token": "[UNK]",
|
| 9 |
+
"word_delimiter_token": "|"
|
| 10 |
+
}
|
vocab.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
",": 56,
|
| 3 |
+
".": 59,
|
| 4 |
+
"?": 64,
|
| 5 |
+
"[PAD]": 72,
|
| 6 |
+
"[UNK]": 71,
|
| 7 |
+
"|": 19,
|
| 8 |
+
"ँ": 46,
|
| 9 |
+
"ं": 20,
|
| 10 |
+
"अ": 41,
|
| 11 |
+
"आ": 54,
|
| 12 |
+
"इ": 0,
|
| 13 |
+
"ई": 15,
|
| 14 |
+
"उ": 22,
|
| 15 |
+
"ऊ": 60,
|
| 16 |
+
"ऋ": 37,
|
| 17 |
+
"ए": 34,
|
| 18 |
+
"ऐ": 29,
|
| 19 |
+
"ऑ": 35,
|
| 20 |
+
"ओ": 13,
|
| 21 |
+
"औ": 26,
|
| 22 |
+
"क": 23,
|
| 23 |
+
"ख": 36,
|
| 24 |
+
"ग": 7,
|
| 25 |
+
"घ": 42,
|
| 26 |
+
"च": 69,
|
| 27 |
+
"छ": 48,
|
| 28 |
+
"ज": 32,
|
| 29 |
+
"झ": 6,
|
| 30 |
+
"ट": 47,
|
| 31 |
+
"ठ": 8,
|
| 32 |
+
"ड": 27,
|
| 33 |
+
"ढ": 57,
|
| 34 |
+
"ण": 67,
|
| 35 |
+
"त": 61,
|
| 36 |
+
"थ": 65,
|
| 37 |
+
"द": 62,
|
| 38 |
+
"ध": 3,
|
| 39 |
+
"न": 25,
|
| 40 |
+
"प": 18,
|
| 41 |
+
"फ": 17,
|
| 42 |
+
"ब": 31,
|
| 43 |
+
"भ": 14,
|
| 44 |
+
"म": 55,
|
| 45 |
+
"य": 45,
|
| 46 |
+
"र": 11,
|
| 47 |
+
"ल": 30,
|
| 48 |
+
"व": 24,
|
| 49 |
+
"श": 52,
|
| 50 |
+
"ष": 9,
|
| 51 |
+
"स": 49,
|
| 52 |
+
"ह": 63,
|
| 53 |
+
"़": 2,
|
| 54 |
+
"ऽ": 53,
|
| 55 |
+
"ा": 66,
|
| 56 |
+
"ि": 58,
|
| 57 |
+
"ी": 43,
|
| 58 |
+
"ु": 51,
|
| 59 |
+
"ू": 10,
|
| 60 |
+
"ृ": 40,
|
| 61 |
+
"े": 38,
|
| 62 |
+
"ै": 5,
|
| 63 |
+
"ॉ": 50,
|
| 64 |
+
"ो": 44,
|
| 65 |
+
"ौ": 21,
|
| 66 |
+
"्": 33,
|
| 67 |
+
"क़": 16,
|
| 68 |
+
"ख़": 68,
|
| 69 |
+
"ग़": 12,
|
| 70 |
+
"ज़": 28,
|
| 71 |
+
"ड़": 39,
|
| 72 |
+
"ढ़": 70,
|
| 73 |
+
"फ़": 1,
|
| 74 |
+
"ॠ": 4
|
| 75 |
+
}
|