Hugging Face's logo

GetmanY1
/
wav2vec2-conformer-rel-pos-base-fi-ft

Safetensors
Model card Files
xet
Community
GetmanY1 commited on
Commit
7fe9ef7
·
verified ·
1 Parent(s): eee0153

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. converted/config.json +109 -0
  2. converted/model.safetensors +3 -0
  3. converted/preprocessor_config.json +10 -0
  4. converted/special_tokens_map.json +6 -0
  5. converted/tokenizer_config.json +49 -0
  6. converted/vocab.json +36 -0
converted/config.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "adapter_kernel_size": 3,
4
+ "adapter_stride": 2,
5
+ "add_adapter": false,
6
+ "apply_spec_augment": true,
7
+ "architectures": [
8
+ "Wav2Vec2ConformerForCTC"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 1,
12
+ "classifier_proj_size": 256,
13
+ "codevector_dim": 256,
14
+ "conformer_conv_dropout": 0.1,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": false,
17
+ "conv_depthwise_kernel_size": 31,
18
+ "conv_dim": [
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512
26
+ ],
27
+ "conv_kernel": [
28
+ 10,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 2,
34
+ 2
35
+ ],
36
+ "conv_stride": [
37
+ 5,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2
44
+ ],
45
+ "ctc_loss_reduction": "sum",
46
+ "ctc_zero_infinity": false,
47
+ "diversity_loss_weight": 0.1,
48
+ "dtype": "float32",
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_norm": "group",
52
+ "feat_proj_dropout": 0.0,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.1,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.1,
57
+ "hidden_size": 768,
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 3072,
60
+ "layer_norm_eps": 1e-05,
61
+ "layerdrop": 0.1,
62
+ "mask_feature_length": 10,
63
+ "mask_feature_min_masks": 0,
64
+ "mask_feature_prob": 0.0,
65
+ "mask_time_length": 10,
66
+ "mask_time_min_masks": 2,
67
+ "mask_time_prob": 0.05,
68
+ "max_source_positions": 5000,
69
+ "model_type": "wav2vec2-conformer",
70
+ "num_adapter_layers": 3,
71
+ "num_attention_heads": 12,
72
+ "num_codevector_groups": 2,
73
+ "num_codevectors_per_group": 320,
74
+ "num_conv_pos_embedding_groups": 16,
75
+ "num_conv_pos_embeddings": 128,
76
+ "num_feat_extract_layers": 7,
77
+ "num_hidden_layers": 12,
78
+ "num_negatives": 100,
79
+ "output_hidden_size": 768,
80
+ "pad_token_id": 0,
81
+ "position_embeddings_type": "relative",
82
+ "proj_codevector_dim": 256,
83
+ "rotary_embedding_base": 10000,
84
+ "tdnn_dilation": [
85
+ 1,
86
+ 2,
87
+ 3,
88
+ 1,
89
+ 1
90
+ ],
91
+ "tdnn_dim": [
92
+ 512,
93
+ 512,
94
+ 512,
95
+ 512,
96
+ 1500
97
+ ],
98
+ "tdnn_kernel": [
99
+ 5,
100
+ 3,
101
+ 3,
102
+ 1,
103
+ 1
104
+ ],
105
+ "transformers_version": "4.57.0.dev0",
106
+ "use_weighted_layer_sum": false,
107
+ "vocab_size": 34,
108
+ "xvector_output_dim": 512
109
+ }
converted/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03022eb1e3239d79772afc8fa71929ceea0e63d07692c748397f1bc487e8b3f6
3
+ size 719161560
converted/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,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": false,
9
+ "sampling_rate": 16000
10
+ }
converted/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
converted/tokenizer_config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
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
+ }
converted/vocab.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<pad>": 0,
4
+ "<s>": 1,
5
+ "<unk>": 3,
6
+ "a": 16,
7
+ "b": 27,
8
+ "c": 28,
9
+ "d": 23,
10
+ "e": 19,
11
+ "f": 26,
12
+ "g": 25,
13
+ "h": 8,
14
+ "i": 9,
15
+ "j": 11,
16
+ "k": 21,
17
+ "l": 20,
18
+ "m": 18,
19
+ "n": 10,
20
+ "o": 7,
21
+ "p": 15,
22
+ "q": 31,
23
+ "r": 22,
24
+ "s": 17,
25
+ "t": 14,
26
+ "u": 6,
27
+ "v": 5,
28
+ "w": 30,
29
+ "x": 32,
30
+ "y": 13,
31
+ "z": 29,
32
+ "|": 4,
33
+ "ä": 12,
34
+ "å": 33,
35
+ "ö": 24
36
+ }