Hugging Face's logo

bishaltwr
/
wav2vec2-large-mms-1b-nepali

Safetensors
wav2vec2
Generated from Trainer
Model card Files Community
1
bishaltwr commited on
Commit
c021cb9
·
verified ·
1 Parent(s): 6cd6645

Update tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +47 -47
tokenizer_config.json CHANGED
@@ -1,47 +1,47 @@
1
- {
2
- "added_tokens_decoder": {
3
- "91": {
4
- "content": "[UNK]",
5
- "lstrip": true,
6
- "normalized": false,
7
- "rstrip": true,
8
- "single_word": false,
9
- "special": false
10
- },
11
- "92": {
12
- "content": "[PAD]",
13
- "lstrip": true,
14
- "normalized": false,
15
- "rstrip": true,
16
- "single_word": false,
17
- "special": false
18
- },
19
- "93": {
20
- "content": "<s>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "94": {
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
- "replace_word_delimiter_char": " ",
43
- "target_lang": "npi",
44
- "tokenizer_class": "Wav2Vec2CTCTokenizer",
45
- "unk_token": "[unk]",
46
- "word_delimiter_token": "|"
47
- }
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "91": {
4
+ "content": "[unk]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "92": {
12
+ "content": "[pad]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "93": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "94": {
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
+ "replace_word_delimiter_char": " ",
43
+ "target_lang": "npi",
44
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
45
+ "unk_token": "[unk]",
46
+ "word_delimiter_token": "|"
47
+ }