trysem commited on
Commit
cd1db66
1 Parent(s): efaeddf

Update tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +1 -48
tokenizer_config.json CHANGED
@@ -1,48 +1 @@
1
- {
2
- "added_tokens_decoder": {
3
- "75": {
4
- "content": "[UNK]",
5
- "lstrip": true,
6
- "normalized": false,
7
- "rstrip": true,
8
- "single_word": false,
9
- "special": false
10
- },
11
- "76": {
12
- "content": "[PAD]",
13
- "lstrip": true,
14
- "normalized": false,
15
- "rstrip": true,
16
- "single_word": false,
17
- "special": false
18
- },
19
- "77": {
20
- "content": "<s>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "78": {
28
- "content": "</s>",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- }
35
- },
36
- "bos_token": "<s>",
37
- "clean_up_tokenization_spaces": true,
38
- "do_lower_case": false,
39
- "eos_token": "</s>",
40
- "model_max_length": 1000000000000000019884624838656,
41
- "pad_token": "[PAD]",
42
- "processor_class": "Wav2Vec2ProcessorWithLM",
43
- "replace_word_delimiter_char": " ",
44
- "target_lang": null,
45
- "tokenizer_class": "Wav2Vec2CTCTokenizer",
46
- "unk_token": "[UNK]",
47
- "word_delimiter_token": "|"
48
- }
 
1
+ {"unk_token": "<unk>", "bos_token": null, "eos_token": null, "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/dbfs/FileStore/trysem/Models/X-LSR_CV_60_EP/checkpoint-26800", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2ProcessorWithLM"}