Upload tokenizer
Browse files- added_tokens.json +107 -106
- special_tokens_map.json +16 -3
- tokenizer_config.json +2 -3
added_tokens.json
CHANGED
@@ -1,108 +1,109 @@
|
|
1 |
{
|
2 |
-
"<|af|>":
|
3 |
-
"<|am|>":
|
4 |
-
"<|ar|>":
|
5 |
-
"<|as|>":
|
6 |
-
"<|az|>":
|
7 |
-
"<|ba|>":
|
8 |
-
"<|be|>":
|
9 |
-
"<|bg|>":
|
10 |
-
"<|bn|>":
|
11 |
-
"<|bo|>":
|
12 |
-
"<|br|>":
|
13 |
-
"<|bs|>":
|
14 |
-
"<|ca|>":
|
15 |
-
"<|cs|>":
|
16 |
-
"<|cy|>":
|
17 |
-
"<|da|>":
|
18 |
-
"<|de|>":
|
19 |
-
"<|el|>":
|
20 |
-
"<|
|
21 |
-
"<|
|
22 |
-
"<|
|
23 |
-
"<|
|
24 |
-
"<|
|
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 |
-
"<|
|
63 |
-
"<|
|
64 |
-
"<|
|
65 |
-
"<|
|
66 |
-
"<|
|
67 |
-
"<|
|
68 |
-
"<|
|
69 |
-
"<|
|
70 |
-
"<|
|
71 |
-
"<|
|
72 |
-
"<|
|
73 |
-
"<|
|
74 |
-
"<|
|
75 |
-
"<|
|
76 |
-
"<|
|
77 |
-
"<|
|
78 |
-
"<|
|
79 |
-
"<|
|
80 |
-
"<|
|
81 |
-
"<|
|
82 |
-
"<|
|
83 |
-
"<|
|
84 |
-
"<|
|
85 |
-
"<|
|
86 |
-
"<|
|
87 |
-
"<|
|
88 |
-
"<|
|
89 |
-
"<|
|
90 |
-
"<|
|
91 |
-
"<|
|
92 |
-
"<|
|
93 |
-
"<|
|
94 |
-
"<|
|
95 |
-
"<|
|
96 |
-
"<|
|
97 |
-
"<|
|
98 |
-
"<|
|
99 |
-
"<|
|
100 |
-
"<|
|
101 |
-
"<|
|
102 |
-
"<|
|
103 |
-
"<|
|
104 |
-
"<|
|
105 |
-
"<|
|
106 |
-
"<|
|
107 |
-
"<|
|
|
|
108 |
}
|
|
|
1 |
{
|
2 |
+
"<|af|>": 50327,
|
3 |
+
"<|am|>": 50334,
|
4 |
+
"<|ar|>": 50272,
|
5 |
+
"<|as|>": 50350,
|
6 |
+
"<|az|>": 50304,
|
7 |
+
"<|ba|>": 50355,
|
8 |
+
"<|be|>": 50330,
|
9 |
+
"<|bg|>": 50292,
|
10 |
+
"<|bn|>": 50302,
|
11 |
+
"<|bo|>": 50347,
|
12 |
+
"<|br|>": 50309,
|
13 |
+
"<|bs|>": 50315,
|
14 |
+
"<|ca|>": 50270,
|
15 |
+
"<|cs|>": 50283,
|
16 |
+
"<|cy|>": 50297,
|
17 |
+
"<|da|>": 50285,
|
18 |
+
"<|de|>": 50261,
|
19 |
+
"<|el|>": 50281,
|
20 |
+
"<|endoftext|>": 50257,
|
21 |
+
"<|en|>": 50259,
|
22 |
+
"<|es|>": 50262,
|
23 |
+
"<|et|>": 50307,
|
24 |
+
"<|eu|>": 50310,
|
25 |
+
"<|fa|>": 50300,
|
26 |
+
"<|fi|>": 50277,
|
27 |
+
"<|fo|>": 50338,
|
28 |
+
"<|fr|>": 50265,
|
29 |
+
"<|gl|>": 50319,
|
30 |
+
"<|gu|>": 50333,
|
31 |
+
"<|haw|>": 50352,
|
32 |
+
"<|ha|>": 50354,
|
33 |
+
"<|hi|>": 50276,
|
34 |
+
"<|hr|>": 50291,
|
35 |
+
"<|ht|>": 50339,
|
36 |
+
"<|hu|>": 50286,
|
37 |
+
"<|hy|>": 50312,
|
38 |
+
"<|id|>": 50275,
|
39 |
+
"<|is|>": 50311,
|
40 |
+
"<|it|>": 50274,
|
41 |
+
"<|iw|>": 50279,
|
42 |
+
"<|ja|>": 50266,
|
43 |
+
"<|jw|>": 50356,
|
44 |
+
"<|ka|>": 50329,
|
45 |
+
"<|kk|>": 50316,
|
46 |
+
"<|km|>": 50323,
|
47 |
+
"<|kn|>": 50306,
|
48 |
+
"<|ko|>": 50264,
|
49 |
+
"<|la|>": 50294,
|
50 |
+
"<|lb|>": 50345,
|
51 |
+
"<|ln|>": 50353,
|
52 |
+
"<|lo|>": 50336,
|
53 |
+
"<|lt|>": 50293,
|
54 |
+
"<|lv|>": 50301,
|
55 |
+
"<|mg|>": 50349,
|
56 |
+
"<|mi|>": 50295,
|
57 |
+
"<|mk|>": 50308,
|
58 |
+
"<|ml|>": 50296,
|
59 |
+
"<|mn|>": 50314,
|
60 |
+
"<|mr|>": 50320,
|
61 |
+
"<|ms|>": 50282,
|
62 |
+
"<|mt|>": 50343,
|
63 |
+
"<|my|>": 50346,
|
64 |
+
"<|ne|>": 50313,
|
65 |
+
"<|nl|>": 50271,
|
66 |
+
"<|nn|>": 50342,
|
67 |
+
"<|nocaptions|>": 50362,
|
68 |
+
"<|notimestamps|>": 50363,
|
69 |
+
"<|no|>": 50288,
|
70 |
+
"<|oc|>": 50328,
|
71 |
+
"<|pa|>": 50321,
|
72 |
+
"<|pl|>": 50269,
|
73 |
+
"<|ps|>": 50340,
|
74 |
+
"<|pt|>": 50267,
|
75 |
+
"<|ro|>": 50284,
|
76 |
+
"<|ru|>": 50263,
|
77 |
+
"<|sa|>": 50344,
|
78 |
+
"<|sd|>": 50332,
|
79 |
+
"<|si|>": 50322,
|
80 |
+
"<|sk|>": 50298,
|
81 |
+
"<|sl|>": 50305,
|
82 |
+
"<|sn|>": 50324,
|
83 |
+
"<|so|>": 50326,
|
84 |
+
"<|sq|>": 50317,
|
85 |
+
"<|sr|>": 50303,
|
86 |
+
"<|startoflm|>": 50360,
|
87 |
+
"<|startofprev|>": 50361,
|
88 |
+
"<|startoftranscript|>": 50258,
|
89 |
+
"<|su|>": 50357,
|
90 |
+
"<|sv|>": 50273,
|
91 |
+
"<|sw|>": 50318,
|
92 |
+
"<|ta|>": 50287,
|
93 |
+
"<|te|>": 50299,
|
94 |
+
"<|tg|>": 50331,
|
95 |
+
"<|th|>": 50289,
|
96 |
+
"<|tk|>": 50341,
|
97 |
+
"<|tl|>": 50348,
|
98 |
+
"<|transcribe|>": 50359,
|
99 |
+
"<|translate|>": 50358,
|
100 |
+
"<|tr|>": 50268,
|
101 |
+
"<|tt|>": 50351,
|
102 |
+
"<|uk|>": 50280,
|
103 |
+
"<|ur|>": 50290,
|
104 |
+
"<|uz|>": 50337,
|
105 |
+
"<|vi|>": 50278,
|
106 |
+
"<|yi|>": 50335,
|
107 |
+
"<|yo|>": 50325,
|
108 |
+
"<|zh|>": 50260
|
109 |
}
|
special_tokens_map.json
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
|
|
3 |
"<|startoftranscript|>",
|
4 |
"<|en|>",
|
5 |
"<|zh|>",
|
@@ -107,13 +108,25 @@
|
|
107 |
"<|nocaptions|>",
|
108 |
"<|notimestamps|>"
|
109 |
],
|
110 |
-
"bos_token":
|
111 |
-
|
112 |
-
|
|
|
|
|
|
|
|
|
|
|
113 |
"content": "<|endoftext|>",
|
114 |
"lstrip": false,
|
115 |
"normalized": true,
|
116 |
"rstrip": false,
|
117 |
"single_word": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
118 |
}
|
119 |
}
|
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
+
"<|endoftext|>",
|
4 |
"<|startoftranscript|>",
|
5 |
"<|en|>",
|
6 |
"<|zh|>",
|
|
|
108 |
"<|nocaptions|>",
|
109 |
"<|notimestamps|>"
|
110 |
],
|
111 |
+
"bos_token": {
|
112 |
+
"content": "<|endoftext|>",
|
113 |
+
"lstrip": false,
|
114 |
+
"normalized": true,
|
115 |
+
"rstrip": false,
|
116 |
+
"single_word": false
|
117 |
+
},
|
118 |
+
"eos_token": {
|
119 |
"content": "<|endoftext|>",
|
120 |
"lstrip": false,
|
121 |
"normalized": true,
|
122 |
"rstrip": false,
|
123 |
"single_word": false
|
124 |
+
},
|
125 |
+
"unk_token": {
|
126 |
+
"content": "",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": true,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false
|
131 |
}
|
132 |
}
|
tokenizer_config.json
CHANGED
@@ -19,14 +19,13 @@
|
|
19 |
},
|
20 |
"errors": "replace",
|
21 |
"model_max_length": 1024,
|
22 |
-
"name_or_path": "
|
23 |
"pad_token": null,
|
24 |
-
"processor_class": "WhisperProcessor",
|
25 |
"special_tokens_map_file": null,
|
26 |
"tokenizer_class": "WhisperTokenizer",
|
27 |
"unk_token": {
|
28 |
"__type": "AddedToken",
|
29 |
-
"content": "
|
30 |
"lstrip": false,
|
31 |
"normalized": true,
|
32 |
"rstrip": false,
|
|
|
19 |
},
|
20 |
"errors": "replace",
|
21 |
"model_max_length": 1024,
|
22 |
+
"name_or_path": "whisper-multi/test_added_eot",
|
23 |
"pad_token": null,
|
|
|
24 |
"special_tokens_map_file": null,
|
25 |
"tokenizer_class": "WhisperTokenizer",
|
26 |
"unk_token": {
|
27 |
"__type": "AddedToken",
|
28 |
+
"content": "",
|
29 |
"lstrip": false,
|
30 |
"normalized": true,
|
31 |
"rstrip": false,
|