iulik-pisik
commited on
Commit
•
fb34750
1
Parent(s):
7d2561a
Add tokenizer
Browse files- special_tokens_map.json +139 -0
- tokenizer.json +0 -0
- tokenizer_config.json +36 -0
- vocab.json +0 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,139 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|endoftext|>",
|
4 |
+
"<|startoftranscript|>",
|
5 |
+
"<|en|>",
|
6 |
+
"<|zh|>",
|
7 |
+
"<|de|>",
|
8 |
+
"<|es|>",
|
9 |
+
"<|ru|>",
|
10 |
+
"<|ko|>",
|
11 |
+
"<|fr|>",
|
12 |
+
"<|ja|>",
|
13 |
+
"<|pt|>",
|
14 |
+
"<|tr|>",
|
15 |
+
"<|pl|>",
|
16 |
+
"<|ca|>",
|
17 |
+
"<|nl|>",
|
18 |
+
"<|ar|>",
|
19 |
+
"<|sv|>",
|
20 |
+
"<|it|>",
|
21 |
+
"<|id|>",
|
22 |
+
"<|hi|>",
|
23 |
+
"<|fi|>",
|
24 |
+
"<|vi|>",
|
25 |
+
"<|he|>",
|
26 |
+
"<|uk|>",
|
27 |
+
"<|el|>",
|
28 |
+
"<|ms|>",
|
29 |
+
"<|cs|>",
|
30 |
+
"<|ro|>",
|
31 |
+
"<|da|>",
|
32 |
+
"<|hu|>",
|
33 |
+
"<|ta|>",
|
34 |
+
"<|no|>",
|
35 |
+
"<|th|>",
|
36 |
+
"<|ur|>",
|
37 |
+
"<|hr|>",
|
38 |
+
"<|bg|>",
|
39 |
+
"<|lt|>",
|
40 |
+
"<|la|>",
|
41 |
+
"<|mi|>",
|
42 |
+
"<|ml|>",
|
43 |
+
"<|cy|>",
|
44 |
+
"<|sk|>",
|
45 |
+
"<|te|>",
|
46 |
+
"<|fa|>",
|
47 |
+
"<|lv|>",
|
48 |
+
"<|bn|>",
|
49 |
+
"<|sr|>",
|
50 |
+
"<|az|>",
|
51 |
+
"<|sl|>",
|
52 |
+
"<|kn|>",
|
53 |
+
"<|et|>",
|
54 |
+
"<|mk|>",
|
55 |
+
"<|br|>",
|
56 |
+
"<|eu|>",
|
57 |
+
"<|is|>",
|
58 |
+
"<|hy|>",
|
59 |
+
"<|ne|>",
|
60 |
+
"<|mn|>",
|
61 |
+
"<|bs|>",
|
62 |
+
"<|kk|>",
|
63 |
+
"<|sq|>",
|
64 |
+
"<|sw|>",
|
65 |
+
"<|gl|>",
|
66 |
+
"<|mr|>",
|
67 |
+
"<|pa|>",
|
68 |
+
"<|si|>",
|
69 |
+
"<|km|>",
|
70 |
+
"<|sn|>",
|
71 |
+
"<|yo|>",
|
72 |
+
"<|so|>",
|
73 |
+
"<|af|>",
|
74 |
+
"<|oc|>",
|
75 |
+
"<|ka|>",
|
76 |
+
"<|be|>",
|
77 |
+
"<|tg|>",
|
78 |
+
"<|sd|>",
|
79 |
+
"<|gu|>",
|
80 |
+
"<|am|>",
|
81 |
+
"<|yi|>",
|
82 |
+
"<|lo|>",
|
83 |
+
"<|uz|>",
|
84 |
+
"<|fo|>",
|
85 |
+
"<|ht|>",
|
86 |
+
"<|ps|>",
|
87 |
+
"<|tk|>",
|
88 |
+
"<|nn|>",
|
89 |
+
"<|mt|>",
|
90 |
+
"<|sa|>",
|
91 |
+
"<|lb|>",
|
92 |
+
"<|my|>",
|
93 |
+
"<|bo|>",
|
94 |
+
"<|tl|>",
|
95 |
+
"<|mg|>",
|
96 |
+
"<|as|>",
|
97 |
+
"<|tt|>",
|
98 |
+
"<|haw|>",
|
99 |
+
"<|ln|>",
|
100 |
+
"<|ha|>",
|
101 |
+
"<|ba|>",
|
102 |
+
"<|jw|>",
|
103 |
+
"<|su|>",
|
104 |
+
"<|translate|>",
|
105 |
+
"<|transcribe|>",
|
106 |
+
"<|startoflm|>",
|
107 |
+
"<|startofprev|>",
|
108 |
+
"<|nocaptions|>",
|
109 |
+
"<|notimestamps|>"
|
110 |
+
],
|
111 |
+
"bos_token": {
|
112 |
+
"content": "<|endoftext|>",
|
113 |
+
"lstrip": false,
|
114 |
+
"normalized": false,
|
115 |
+
"rstrip": false,
|
116 |
+
"single_word": false
|
117 |
+
},
|
118 |
+
"eos_token": {
|
119 |
+
"content": "<|endoftext|>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false
|
124 |
+
},
|
125 |
+
"pad_token": {
|
126 |
+
"content": "<|endoftext|>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false
|
131 |
+
},
|
132 |
+
"unk_token": {
|
133 |
+
"content": "<|endoftext|>",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": false,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false
|
138 |
+
}
|
139 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"eos_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"errors": "replace",
|
21 |
+
"model_max_length": 1024,
|
22 |
+
"name_or_path": "openai/whisper-base",
|
23 |
+
"pad_token": null,
|
24 |
+
"processor_class": "WhisperProcessor",
|
25 |
+
"return_attention_mask": false,
|
26 |
+
"special_tokens_map_file": null,
|
27 |
+
"tokenizer_class": "WhisperTokenizer",
|
28 |
+
"unk_token": {
|
29 |
+
"__type": "AddedToken",
|
30 |
+
"content": "",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false
|
35 |
+
}
|
36 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|