Hugging Face's logo

glossKit-ASR
/
wav2vec2-large-xlsr-53-zza

Automatic Speech Recognition
Safetensors
PyTorch
Zaza
wav2vec2
audio
Model card Files
xet
 Community
glossKit-ASR commited on
Commit
8d2faae
·
verified ·
1 Parent(s): 13f1b2a

Update processor: 2026-05-19T20:10:35.023906

Browse files
Files changed (4) hide show
  1. preprocessor_config.json +10 -0
  2. special_tokens_map.json +30 -0
  3. tokenizer_config.json +49 -0
  4. vocab.json +57 -0
preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": true,
5
+ "normalized": false,
6
+ "rstrip": true,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": true,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": true,
19
+ "normalized": false,
20
+ "rstrip": true,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "[UNK]",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": true,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "41": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "42": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "43": {
20
+ "content": "<s>",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "44": {
28
+ "content": "</s>",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": false
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": false,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "extra_special_tokens": {},
41
+ "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "[PAD]",
43
+ "processor_class": "Wav2Vec2Processor",
44
+ "replace_word_delimiter_char": " ",
45
+ "target_lang": null,
46
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
47
+ "unk_token": "[UNK]",
48
+ "word_delimiter_token": "|"
49
+ }
vocab.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "0": 45,
3
+ "1": 46,
4
+ "3": 47,
5
+ "4": 48,
6
+ "6": 49,
7
+ "8": 50,
8
+ "</s>": 44,
9
+ "<s>": 43,
10
+ "[PAD]": 42,
11
+ "[UNK]": 41,
12
+ "a": 3,
13
+ "b": 4,
14
+ "c": 28,
15
+ "d": 27,
16
+ "e": 5,
17
+ "f": 33,
18
+ "g": 7,
19
+ "h": 32,
20
+ "i": 6,
21
+ "j": 16,
22
+ "k": 29,
23
+ "l": 25,
24
+ "m": 15,
25
+ "n": 19,
26
+ "o": 24,
27
+ "p": 17,
28
+ "q": 14,
29
+ "r": 2,
30
+ "s": 23,
31
+ "t": 8,
32
+ "u": 22,
33
+ "v": 0,
34
+ "w": 36,
35
+ "x": 13,
36
+ "y": 10,
37
+ "z": 30,
38
+ "|": 18,
39
+ "ç": 20,
40
+ "ê": 11,
41
+ "î": 31,
42
+ "ö": 51,
43
+ "û": 26,
44
+ "ü": 52,
45
+ "đ": 12,
46
+ "ğ": 53,
47
+ "ġ": 39,
48
+ "ħ": 1,
49
+ "ı": 54,
50
+ "ŋ": 35,
51
+ "ř": 37,
52
+ "ş": 34,
53
+ "ɫ": 21,
54
+ "ʕ": 38,
55
+ "̣": 40,
56
+ "ḥ": 9
57
+ }