Upload tokenizer
Browse files- README.md +3 -3
- added_tokens.json +2 -2
- tokenizer_config.json +4 -4
- vocab.json +50 -59
README.md
CHANGED
@@ -1,10 +1,10 @@
|
|
1 |
---
|
2 |
-
license: apache-2.0
|
3 |
-
tags:
|
4 |
-
- generated_from_trainer
|
5 |
base_model: facebook/wav2vec2-xls-r-300m
|
6 |
datasets:
|
7 |
- make_dataset
|
|
|
|
|
|
|
8 |
model-index:
|
9 |
- name: wav2vec2-large-xls-r-300m-korean-g
|
10 |
results: []
|
|
|
1 |
---
|
|
|
|
|
|
|
2 |
base_model: facebook/wav2vec2-xls-r-300m
|
3 |
datasets:
|
4 |
- make_dataset
|
5 |
+
license: apache-2.0
|
6 |
+
tags:
|
7 |
+
- generated_from_trainer
|
8 |
model-index:
|
9 |
- name: wav2vec2-large-xls-r-300m-korean-g
|
10 |
results: []
|
added_tokens.json
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
{
|
2 |
-
"</s>":
|
3 |
-
"<s>":
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"</s>": 52,
|
3 |
+
"<s>": 51
|
4 |
}
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
-
"
|
4 |
"content": "[UNK]",
|
5 |
"lstrip": true,
|
6 |
"normalized": false,
|
@@ -8,7 +8,7 @@
|
|
8 |
"single_word": false,
|
9 |
"special": false
|
10 |
},
|
11 |
-
"
|
12 |
"content": "[PAD]",
|
13 |
"lstrip": true,
|
14 |
"normalized": false,
|
@@ -16,7 +16,7 @@
|
|
16 |
"single_word": false,
|
17 |
"special": false
|
18 |
},
|
19 |
-
"
|
20 |
"content": "<s>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
@@ -24,7 +24,7 @@
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
"content": "</s>",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
+
"49": {
|
4 |
"content": "[UNK]",
|
5 |
"lstrip": true,
|
6 |
"normalized": false,
|
|
|
8 |
"single_word": false,
|
9 |
"special": false
|
10 |
},
|
11 |
+
"50": {
|
12 |
"content": "[PAD]",
|
13 |
"lstrip": true,
|
14 |
"normalized": false,
|
|
|
16 |
"single_word": false,
|
17 |
"special": false
|
18 |
},
|
19 |
+
"51": {
|
20 |
"content": "<s>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
+
"52": {
|
28 |
"content": "</s>",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
vocab.json
CHANGED
@@ -1,62 +1,53 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"2": 3,
|
5 |
-
"3": 4,
|
6 |
-
"4": 5,
|
7 |
-
"5": 6,
|
8 |
-
"6": 7,
|
9 |
-
"7": 8,
|
10 |
-
"8": 9,
|
11 |
-
"9": 10,
|
12 |
-
"[PAD]": 59,
|
13 |
-
"[UNK]": 58,
|
14 |
"|": 0,
|
15 |
-
"γ±":
|
16 |
-
"γ²":
|
17 |
-
"γ³":
|
18 |
-
"γ΄":
|
19 |
-
"γ΅":
|
20 |
-
"γΆ":
|
21 |
-
"γ·":
|
22 |
-
"γΈ":
|
23 |
-
"γΉ":
|
24 |
-
"γΊ":
|
25 |
-
"
|
26 |
-
"
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"
|
30 |
-
"
|
31 |
-
"
|
32 |
-
"
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"
|
36 |
-
"
|
37 |
-
"
|
38 |
-
"
|
39 |
-
"
|
40 |
-
"
|
41 |
-
"
|
42 |
-
"
|
43 |
-
"
|
44 |
-
"
|
45 |
-
"
|
46 |
-
"
|
47 |
-
"
|
48 |
-
"
|
49 |
-
"
|
50 |
-
"
|
51 |
-
"
|
52 |
-
"
|
53 |
-
"
|
54 |
-
"
|
55 |
-
"
|
56 |
-
"
|
57 |
-
"
|
58 |
-
"
|
59 |
-
"
|
60 |
-
"
|
61 |
-
"
|
|
|
62 |
}
|
|
|
1 |
{
|
2 |
+
"[PAD]": 50,
|
3 |
+
"[UNK]": 49,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
"|": 0,
|
5 |
+
"γ±": 1,
|
6 |
+
"γ²": 2,
|
7 |
+
"γ³": 3,
|
8 |
+
"γ΄": 4,
|
9 |
+
"γ΅": 5,
|
10 |
+
"γΆ": 6,
|
11 |
+
"γ·": 7,
|
12 |
+
"γΈ": 8,
|
13 |
+
"γΉ": 9,
|
14 |
+
"γΊ": 10,
|
15 |
+
"γ»": 11,
|
16 |
+
"γΌ": 12,
|
17 |
+
"γ
": 13,
|
18 |
+
"γ
": 14,
|
19 |
+
"γ
": 15,
|
20 |
+
"γ
": 16,
|
21 |
+
"γ
": 17,
|
22 |
+
"γ
": 18,
|
23 |
+
"γ
": 19,
|
24 |
+
"γ
": 20,
|
25 |
+
"γ
": 21,
|
26 |
+
"γ
": 22,
|
27 |
+
"γ
": 23,
|
28 |
+
"γ
": 24,
|
29 |
+
"γ
": 25,
|
30 |
+
"γ
": 26,
|
31 |
+
"γ
": 27,
|
32 |
+
"γ
": 28,
|
33 |
+
"γ
": 29,
|
34 |
+
"γ
": 30,
|
35 |
+
"γ
": 31,
|
36 |
+
"γ
": 32,
|
37 |
+
"γ
": 33,
|
38 |
+
"γ
": 34,
|
39 |
+
"γ
": 35,
|
40 |
+
"γ
": 36,
|
41 |
+
"γ
": 37,
|
42 |
+
"γ
": 38,
|
43 |
+
"γ
": 39,
|
44 |
+
"γ
": 40,
|
45 |
+
"γ
": 41,
|
46 |
+
"γ
": 42,
|
47 |
+
"γ
": 43,
|
48 |
+
"γ
": 44,
|
49 |
+
"γ
": 45,
|
50 |
+
"γ
‘": 46,
|
51 |
+
"γ
’": 47,
|
52 |
+
"γ
£": 48
|
53 |
}
|