Hugging Face's logo

alianurrahman
/
wav2vec2-base-indonesian-speech-emotion-recognition

Audio Classification
Transformers
TensorBoard
Safetensors
Indonesian
wav2vec2
fine-tune
Inference Endpoints
Model card Files Metrics Community
alianurrahman commited on
Commit
ef2a7fa
•
1 Parent(s): 037a8ce

Training in progress, epoch 0

Browse files
Files changed (9) hide show
  1. config.json +132 -0
  2. model.safetensors +3 -0
  3. preprocessor_config.json +9 -0
  4. runs/Sep26_16-04-31_macs-mbp/events.out.tfevents.1727341473.macs-mbp.22335.0 +3 -0
  5. runs/Sep26_16-45-36_macs-mbp/events.out.tfevents.1727343937.macs-mbp.22716.0 +3 -0
  6. runs/Sep26_17-43-26_macs-mbp/events.out.tfevents.1727347409.macs-mbp.23037.0 +3 -0
  7. runs/Sep27_10-42-07_macs-mbp/events.out.tfevents.1727408530.macs-mbp.25745.0 +3 -0
  8. runs/Sep27_11-17-34_macs-mbp/events.out.tfevents.1727410657.macs-mbp.26104.0 +3 -0
  9. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,132 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "angry",
61
+ "1": "disgust",
62
+ "2": "fear",
63
+ "3": "happy",
64
+ "4": "sad"
65
+ },
66
+ "initializer_range": 0.02,
67
+ "intermediate_size": 3072,
68
+ "label2id": {
69
+ "angry": "0",
70
+ "disgust": "1",
71
+ "fear": "2",
72
+ "happy": "3",
73
+ "sad": "4"
74
+ },
75
+ "layer_norm_eps": 1e-05,
76
+ "layerdrop": 0.0,
77
+ "mask_channel_length": 10,
78
+ "mask_channel_min_space": 1,
79
+ "mask_channel_other": 0.0,
80
+ "mask_channel_prob": 0.0,
81
+ "mask_channel_selection": "static",
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_min_space": 1,
88
+ "mask_time_other": 0.0,
89
+ "mask_time_prob": 0.05,
90
+ "mask_time_selection": "static",
91
+ "model_type": "wav2vec2",
92
+ "no_mask_channel_overlap": false,
93
+ "no_mask_time_overlap": false,
94
+ "num_adapter_layers": 3,
95
+ "num_attention_heads": 12,
96
+ "num_codevector_groups": 2,
97
+ "num_codevectors_per_group": 320,
98
+ "num_conv_pos_embedding_groups": 16,
99
+ "num_conv_pos_embeddings": 128,
100
+ "num_feat_extract_layers": 7,
101
+ "num_hidden_layers": 12,
102
+ "num_negatives": 100,
103
+ "output_hidden_size": 768,
104
+ "pad_token_id": 0,
105
+ "proj_codevector_dim": 256,
106
+ "tdnn_dilation": [
107
+ 1,
108
+ 2,
109
+ 3,
110
+ 1,
111
+ 1
112
+ ],
113
+ "tdnn_dim": [
114
+ 512,
115
+ 512,
116
+ 512,
117
+ 512,
118
+ 1500
119
+ ],
120
+ "tdnn_kernel": [
121
+ 5,
122
+ 3,
123
+ 3,
124
+ 1,
125
+ 1
126
+ ],
127
+ "torch_dtype": "float32",
128
+ "transformers_version": "4.44.2",
129
+ "use_weighted_layer_sum": false,
130
+ "vocab_size": 32,
131
+ "xvector_output_dim": 512
132
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85fa3652d0c377c7f325cf6e4086b622c1f39230990400f76868936645ad223a
3
+ size 378305452
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
+ }
runs/Sep26_16-04-31_macs-mbp/events.out.tfevents.1727341473.macs-mbp.22335.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6dcd5096be95d8d152384cf124f2bb0e80e83b433d2c76600903e179b668210
3
+ size 7104
runs/Sep26_16-45-36_macs-mbp/events.out.tfevents.1727343937.macs-mbp.22716.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4339343326cf2571f6cd0e3a27bb1bc982a5e545d9cf40de0ffb94ab66ec614
3
+ size 7310
runs/Sep26_17-43-26_macs-mbp/events.out.tfevents.1727347409.macs-mbp.23037.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8780d2b1e771ee2d33088fc588a755a8c7977bbaa711350343fe2080742e007c
3
+ size 9847
runs/Sep27_10-42-07_macs-mbp/events.out.tfevents.1727408530.macs-mbp.25745.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8122be92b3b974dff28578ee3334d2c7f0c4c2a12d1d18de8d167b8487056dd
3
+ size 9847
runs/Sep27_11-17-34_macs-mbp/events.out.tfevents.1727410657.macs-mbp.26104.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41c69a079ab4b763697437b84a6e6b0383a23b08fd774c45f1c88df15f1390a1
3
+ size 7072
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cef364a4a4caf7734d8171b3fbbe5c77bc0bb8791ec20a4edf760f3bf6fce0e
3
+ size 5176