Upload processor
Browse files- preprocessor_config.json +10 -0
- special_tokens_map.json +6 -0
- tokenizer_config.json +11 -0
- vocab.json +69 -0
preprocessor_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 0.0,
|
7 |
+
"processor_class": "Wav2Vec2Processor",
|
8 |
+
"return_attention_mask": true,
|
9 |
+
"sampling_rate": 16000
|
10 |
+
}
|
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 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"do_lower_case": false,
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"pad_token": "[PAD]",
|
6 |
+
"processor_class": "Wav2Vec2Processor",
|
7 |
+
"replace_word_delimiter_char": " ",
|
8 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
9 |
+
"unk_token": "[UNK]",
|
10 |
+
"word_delimiter_token": "|"
|
11 |
+
}
|
vocab.json
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[PAD]": 66,
|
3 |
+
"[UNK]": 65,
|
4 |
+
"|": 55,
|
5 |
+
"ก": 0,
|
6 |
+
"ข": 59,
|
7 |
+
"ค": 64,
|
8 |
+
"ฆ": 1,
|
9 |
+
"ง": 24,
|
10 |
+
"จ": 41,
|
11 |
+
"ฉ": 27,
|
12 |
+
"ช": 37,
|
13 |
+
"ซ": 12,
|
14 |
+
"ฌ": 62,
|
15 |
+
"ญ": 14,
|
16 |
+
"ฎ": 49,
|
17 |
+
"ฏ": 60,
|
18 |
+
"ฐ": 15,
|
19 |
+
"ฒ": 23,
|
20 |
+
"ณ": 13,
|
21 |
+
"ด": 3,
|
22 |
+
"ต": 2,
|
23 |
+
"ถ": 19,
|
24 |
+
"ท": 35,
|
25 |
+
"ธ": 29,
|
26 |
+
"น": 48,
|
27 |
+
"บ": 18,
|
28 |
+
"ป": 11,
|
29 |
+
"ผ": 34,
|
30 |
+
"ฝ": 46,
|
31 |
+
"พ": 47,
|
32 |
+
"ฟ": 30,
|
33 |
+
"ภ": 61,
|
34 |
+
"ม": 36,
|
35 |
+
"ย": 32,
|
36 |
+
"ร": 58,
|
37 |
+
"ฤ": 50,
|
38 |
+
"ล": 7,
|
39 |
+
"ว": 38,
|
40 |
+
"ศ": 53,
|
41 |
+
"ษ": 21,
|
42 |
+
"ส": 44,
|
43 |
+
"ห": 22,
|
44 |
+
"ฬ": 6,
|
45 |
+
"อ": 39,
|
46 |
+
"ฮ": 63,
|
47 |
+
"ะ": 4,
|
48 |
+
"ั": 52,
|
49 |
+
"า": 25,
|
50 |
+
"ำ": 33,
|
51 |
+
"ิ": 43,
|
52 |
+
"ี": 31,
|
53 |
+
"ึ": 5,
|
54 |
+
"ื": 26,
|
55 |
+
"ุ": 51,
|
56 |
+
"ู": 28,
|
57 |
+
"ฺ": 42,
|
58 |
+
"เ": 20,
|
59 |
+
"แ": 45,
|
60 |
+
"โ": 16,
|
61 |
+
"ใ": 8,
|
62 |
+
"ไ": 56,
|
63 |
+
"็": 9,
|
64 |
+
"่": 10,
|
65 |
+
"้": 17,
|
66 |
+
"๊": 57,
|
67 |
+
"๋": 54,
|
68 |
+
"์": 40
|
69 |
+
}
|