Commit
·
1b312bd
1
Parent(s):
1ab65ec
Upload tokenizer
Browse files- added_tokens.json +6 -0
- special_tokens_map.json +6 -0
- tokenizer_config.json +49 -0
- vocab.json +86 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</s>": 2,
|
| 3 |
+
"<pad>": 0,
|
| 4 |
+
"<s>": 1,
|
| 5 |
+
"<unk>": 3
|
| 6 |
+
}
|
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 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": true,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": true,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": false
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<s>",
|
| 13 |
+
"lstrip": true,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": true,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": false
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": true,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": true,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": false
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": true,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": true,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"additional_special_tokens": [],
|
| 37 |
+
"bos_token": "<s>",
|
| 38 |
+
"clean_up_tokenization_spaces": true,
|
| 39 |
+
"do_lower_case": false,
|
| 40 |
+
"eos_token": "</s>",
|
| 41 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 42 |
+
"pad_token": "<pad>",
|
| 43 |
+
"replace_word_delimiter_char": " ",
|
| 44 |
+
"target_lang": null,
|
| 45 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 46 |
+
"tokenizer_file": null,
|
| 47 |
+
"unk_token": "<unk>",
|
| 48 |
+
"word_delimiter_token": "|"
|
| 49 |
+
}
|
vocab.json
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"0": 5,
|
| 3 |
+
"1": 6,
|
| 4 |
+
"2": 7,
|
| 5 |
+
"3": 8,
|
| 6 |
+
"4": 9,
|
| 7 |
+
"5": 10,
|
| 8 |
+
"6": 11,
|
| 9 |
+
"7": 12,
|
| 10 |
+
"8": 13,
|
| 11 |
+
"9": 14,
|
| 12 |
+
"</s>": 2,
|
| 13 |
+
"<pad>": 0,
|
| 14 |
+
"<s>": 1,
|
| 15 |
+
"<unk>": 3,
|
| 16 |
+
"|": 4,
|
| 17 |
+
"ँ": 15,
|
| 18 |
+
"ं": 16,
|
| 19 |
+
"ः": 17,
|
| 20 |
+
"अ": 18,
|
| 21 |
+
"आ": 19,
|
| 22 |
+
"इ": 20,
|
| 23 |
+
"ई": 21,
|
| 24 |
+
"उ": 22,
|
| 25 |
+
"ऊ": 23,
|
| 26 |
+
"ऋ": 24,
|
| 27 |
+
"ए": 25,
|
| 28 |
+
"ऐ": 26,
|
| 29 |
+
"ऑ": 27,
|
| 30 |
+
"ओ": 28,
|
| 31 |
+
"औ": 29,
|
| 32 |
+
"क": 30,
|
| 33 |
+
"ख": 31,
|
| 34 |
+
"ग": 32,
|
| 35 |
+
"घ": 33,
|
| 36 |
+
"ङ": 34,
|
| 37 |
+
"च": 35,
|
| 38 |
+
"छ": 36,
|
| 39 |
+
"ज": 37,
|
| 40 |
+
"झ": 38,
|
| 41 |
+
"ञ": 39,
|
| 42 |
+
"ट": 40,
|
| 43 |
+
"ठ": 41,
|
| 44 |
+
"ड": 42,
|
| 45 |
+
"ढ": 43,
|
| 46 |
+
"ण": 44,
|
| 47 |
+
"त": 45,
|
| 48 |
+
"थ": 46,
|
| 49 |
+
"द": 47,
|
| 50 |
+
"ध": 48,
|
| 51 |
+
"न": 49,
|
| 52 |
+
"प": 50,
|
| 53 |
+
"फ": 51,
|
| 54 |
+
"ब": 52,
|
| 55 |
+
"भ": 53,
|
| 56 |
+
"म": 54,
|
| 57 |
+
"य": 55,
|
| 58 |
+
"र": 56,
|
| 59 |
+
"ल": 57,
|
| 60 |
+
"व": 58,
|
| 61 |
+
"श": 59,
|
| 62 |
+
"ष": 60,
|
| 63 |
+
"स": 61,
|
| 64 |
+
"ह": 62,
|
| 65 |
+
"ा": 63,
|
| 66 |
+
"ि": 64,
|
| 67 |
+
"ी": 65,
|
| 68 |
+
"ु": 66,
|
| 69 |
+
"ू": 67,
|
| 70 |
+
"ृ": 68,
|
| 71 |
+
"ॅ": 69,
|
| 72 |
+
"े": 70,
|
| 73 |
+
"ै": 71,
|
| 74 |
+
"ॉ": 72,
|
| 75 |
+
"ो": 73,
|
| 76 |
+
"ौ": 74,
|
| 77 |
+
"्": 75,
|
| 78 |
+
"क़": 76,
|
| 79 |
+
"ख़": 77,
|
| 80 |
+
"ग़": 78,
|
| 81 |
+
"ज़": 79,
|
| 82 |
+
"ड़": 80,
|
| 83 |
+
"ढ़": 81,
|
| 84 |
+
"फ़": 82,
|
| 85 |
+
"य़": 83
|
| 86 |
+
}
|