Hugging Face's logo

kunal18
/
wav2vec2-conformer-rel-pos-large-medical-intent

Audio Classification
Transformers
TensorBoard
Safetensors
wav2vec2-conformer
Inference Endpoints
Model card Files Metrics Community
kunal18 commited on
Commit
6f3787f
•
1 Parent(s): 30cce3d

Training in progress, epoch 0

Browse files
Files changed (7) hide show
  1. config.json +131 -0
  2. model.safetensors +3 -0
  3. preprocessor_config.json +10 -0
  4. runs/Mar26_11-22-53_d1028/events.out.tfevents.1711466575.d1028.14758.0 +3 -0
  5. runs/Mar26_11-23-52_d1028/events.out.tfevents.1711466633.d1028.14758.1 +3 -0
  6. runs/Mar26_11-24-26_d1028/events.out.tfevents.1711466667.d1028.14758.2 +3 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-conformer-rel-pos-large",
3
+ "activation_dropout": 0.1,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ConformerForSequenceClassification"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 768,
15
+ "conformer_conv_dropout": 0.1,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": true,
18
+ "conv_depthwise_kernel_size": 31,
19
+ "conv_dim": [
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512,
26
+ 512
27
+ ],
28
+ "conv_kernel": [
29
+ 10,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 3,
34
+ 2,
35
+ 2
36
+ ],
37
+ "conv_stride": [
38
+ 5,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2,
44
+ 2
45
+ ],
46
+ "ctc_loss_reduction": "sum",
47
+ "ctc_zero_infinity": false,
48
+ "diversity_loss_weight": 0.1,
49
+ "do_stable_layer_norm": true,
50
+ "eos_token_id": 2,
51
+ "feat_extract_activation": "gelu",
52
+ "feat_extract_dropout": 0.0,
53
+ "feat_extract_norm": "layer",
54
+ "feat_proj_dropout": 0.1,
55
+ "feat_quantizer_dropout": 0.0,
56
+ "final_dropout": 0.1,
57
+ "gradient_checkpointing": false,
58
+ "hidden_act": "swish",
59
+ "hidden_dropout": 0.1,
60
+ "hidden_dropout_prob": 0.1,
61
+ "hidden_size": 1024,
62
+ "id2label": {
63
+ "0": "Abdominal Pain and Weakness",
64
+ "1": "Dermatological Issues",
65
+ "2": "Head and Neck Discomfort",
66
+ "3": "Musculoskeletal Pain",
67
+ "4": "Respiratory and Ear Issues",
68
+ "5": "Wound Trauma"
69
+ },
70
+ "initializer_range": 0.02,
71
+ "intermediate_size": 4096,
72
+ "label2id": {
73
+ "Abdominal Pain and Weakness": 0,
74
+ "Dermatological Issues": 1,
75
+ "Head and Neck Discomfort": 2,
76
+ "Musculoskeletal Pain": 3,
77
+ "Respiratory and Ear Issues": 4,
78
+ "Wound Trauma": 5
79
+ },
80
+ "layer_norm_eps": 1e-05,
81
+ "layerdrop": 0.0,
82
+ "mask_feature_length": 10,
83
+ "mask_feature_min_masks": 0,
84
+ "mask_feature_prob": 0.0,
85
+ "mask_time_length": 10,
86
+ "mask_time_min_masks": 2,
87
+ "mask_time_prob": 0.05,
88
+ "max_source_positions": 5000,
89
+ "model_type": "wav2vec2-conformer",
90
+ "num_adapter_layers": 3,
91
+ "num_attention_heads": 16,
92
+ "num_codevector_groups": 2,
93
+ "num_codevectors_per_group": 320,
94
+ "num_conv_pos_embedding_groups": 16,
95
+ "num_conv_pos_embeddings": 128,
96
+ "num_feat_extract_layers": 7,
97
+ "num_hidden_layers": 24,
98
+ "num_negatives": 100,
99
+ "output_hidden_size": 1024,
100
+ "pad_token_id": 0,
101
+ "position_embeddings_type": "relative",
102
+ "proj_codevector_dim": 768,
103
+ "rotary_embedding_base": 10000,
104
+ "tdnn_dilation": [
105
+ 1,
106
+ 2,
107
+ 3,
108
+ 1,
109
+ 1
110
+ ],
111
+ "tdnn_dim": [
112
+ 512,
113
+ 512,
114
+ 512,
115
+ 512,
116
+ 1500
117
+ ],
118
+ "tdnn_kernel": [
119
+ 5,
120
+ 3,
121
+ 3,
122
+ 1,
123
+ 1
124
+ ],
125
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
126
+ "torch_dtype": "float32",
127
+ "transformers_version": "4.39.1",
128
+ "use_weighted_layer_sum": false,
129
+ "vocab_size": null,
130
+ "xvector_output_dim": 512
131
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b4b2e1477c6587ba37d79f389fb999c0d574b2f41819c7ec4cfb8c02eb09b8b
3
+ size 2475615512
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
+ }
runs/Mar26_11-22-53_d1028/events.out.tfevents.1711466575.d1028.14758.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:436b3442cd334806ad0d045da64d15b18162d5642d88df18ef4d1a40cd0a3787
3
+ size 7049
runs/Mar26_11-23-52_d1028/events.out.tfevents.1711466633.d1028.14758.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:342ae4dc763e62c3740a343c99d9062b6c61b48f9657835e140f9484ffb83ddc
3
+ size 7049
runs/Mar26_11-24-26_d1028/events.out.tfevents.1711466667.d1028.14758.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:316c5853df6723c1d4bd37426fc901546061cc494da2a0d5ccd3daac4c7e7429
3
+ size 8963
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d936e6b7fba5f0c8b04d3265fa71602e6d76dd778926802b262e9b6d28096c44
3
+ size 5048