Hugging Face's logo

Wiam
/
wav2vec2-base-finetuned-ravdess

Audio Classification
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
Wiam commited on
Commit
921e0db
•
1 Parent(s): 515b814

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. .gitignore +1 -0
  2. config.json +138 -0
  3. preprocessor_config.json +9 -0
  4. pytorch_model.bin +3 -0
  5. runs/Aug17_11-58-01_976a2f77c133/events.out.tfevents.1692273492.976a2f77c133.7193.0 +3 -0
  6. runs/Aug17_11-58-34_976a2f77c133/events.out.tfevents.1692273523.976a2f77c133.7193.1 +3 -0
  7. runs/Aug17_11-58-34_976a2f77c133/events.out.tfevents.1692274149.976a2f77c133.7193.2 +3 -0
  8. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base",
3
+ "activation_dropout": 0.0,
4
+ "adapter_attn_dim": null,
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": false,
8
+ "apply_spec_augment": true,
9
+ "architectures": [
10
+ "Wav2Vec2ForSequenceClassification"
11
+ ],
12
+ "attention_dropout": 0.1,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 256,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": false,
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
+ "do_stable_layer_norm": false,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "freeze_feat_extract_train": true,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_size": 768,
59
+ "id2label": {
60
+ "0": "neutral",
61
+ "1": "calm",
62
+ "2": "happy",
63
+ "3": "sad",
64
+ "4": "angry",
65
+ "5": "fearful",
66
+ "6": "disgust",
67
+ "7": "surprised"
68
+ },
69
+ "initializer_range": 0.02,
70
+ "intermediate_size": 3072,
71
+ "label2id": {
72
+ "angry": "4",
73
+ "calm": "1",
74
+ "disgust": "6",
75
+ "fearful": "5",
76
+ "happy": "2",
77
+ "neutral": "0",
78
+ "sad": "3",
79
+ "surprised": "7"
80
+ },
81
+ "layer_norm_eps": 1e-05,
82
+ "layerdrop": 0.0,
83
+ "mask_channel_length": 10,
84
+ "mask_channel_min_space": 1,
85
+ "mask_channel_other": 0.0,
86
+ "mask_channel_prob": 0.0,
87
+ "mask_channel_selection": "static",
88
+ "mask_feature_length": 10,
89
+ "mask_feature_min_masks": 0,
90
+ "mask_feature_prob": 0.0,
91
+ "mask_time_length": 10,
92
+ "mask_time_min_masks": 2,
93
+ "mask_time_min_space": 1,
94
+ "mask_time_other": 0.0,
95
+ "mask_time_prob": 0.05,
96
+ "mask_time_selection": "static",
97
+ "model_type": "wav2vec2",
98
+ "no_mask_channel_overlap": false,
99
+ "no_mask_time_overlap": false,
100
+ "num_adapter_layers": 3,
101
+ "num_attention_heads": 12,
102
+ "num_codevector_groups": 2,
103
+ "num_codevectors_per_group": 320,
104
+ "num_conv_pos_embedding_groups": 16,
105
+ "num_conv_pos_embeddings": 128,
106
+ "num_feat_extract_layers": 7,
107
+ "num_hidden_layers": 12,
108
+ "num_negatives": 100,
109
+ "output_hidden_size": 768,
110
+ "pad_token_id": 0,
111
+ "proj_codevector_dim": 256,
112
+ "tdnn_dilation": [
113
+ 1,
114
+ 2,
115
+ 3,
116
+ 1,
117
+ 1
118
+ ],
119
+ "tdnn_dim": [
120
+ 512,
121
+ 512,
122
+ 512,
123
+ 512,
124
+ 1500
125
+ ],
126
+ "tdnn_kernel": [
127
+ 5,
128
+ 3,
129
+ 3,
130
+ 1,
131
+ 1
132
+ ],
133
+ "torch_dtype": "float32",
134
+ "transformers_version": "4.31.0",
135
+ "use_weighted_layer_sum": false,
136
+ "vocab_size": 32,
137
+ "xvector_output_dim": 512
138
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5803ebd9089c7708acf51cca7e0c3577c2c31368f51ef62dfa2d032aef530f29
3
+ size 378356585
runs/Aug17_11-58-01_976a2f77c133/events.out.tfevents.1692273492.976a2f77c133.7193.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:140859e28926dcb52b420cd4226a1bbd8d141b20c74d0287ac991da9cb9cecb7
3
+ size 6137
runs/Aug17_11-58-34_976a2f77c133/events.out.tfevents.1692273523.976a2f77c133.7193.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ce358daf8e94797dbe037c34173e1fe6ad3802d4a428ec2c6e44555f46e4391
3
+ size 6137
runs/Aug17_11-58-34_976a2f77c133/events.out.tfevents.1692274149.976a2f77c133.7193.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e469d75d4740334c5a9486e4d8e9ae28f9a941e65a1624ddf91ce76dfbf32b22
3
+ size 6454
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a99718184e6db77d014ad099fd52f7584a0c1eef895970959300ef242504db1
3
+ size 4027