Hugging Face's logo

Paranchai
/
wav2vec2-large-xlsr-53-th-speech-emotion-recognition-4c

Audio Classification
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Paranchai commited on
Commit
00bc362
·
verified ·
1 Parent(s): f63044f

Training in progress, epoch 0

Browse files
Files changed (5) hide show
  1. config.json +128 -0
  2. model.safetensors +3 -0
  3. preprocessor_config.json +9 -0
  4. runs/Oct14_19-27-58_ba0c8d9a2d7c/events.out.tfevents.1728934081.ba0c8d9a2d7c.2094.0 +3 -0
  5. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "airesearch/wav2vec2-large-xlsr-53-th",
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": 768,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": true,
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": "mean",
46
+ "ctc_zero_infinity": false,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_stable_layer_norm": true,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "layer",
53
+ "feat_proj_dropout": 0.0,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.0,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_size": 1024,
59
+ "id2label": {
60
+ "0": "Anger",
61
+ "1": "Happiness",
62
+ "2": "Neutral",
63
+ "3": "Sadness"
64
+ },
65
+ "initializer_range": 0.02,
66
+ "intermediate_size": 4096,
67
+ "label2id": {
68
+ "Anger": "0",
69
+ "Happiness": "1",
70
+ "Neutral": "2",
71
+ "Sadness": "3"
72
+ },
73
+ "layer_norm_eps": 1e-05,
74
+ "layerdrop": 0.1,
75
+ "mask_channel_length": 10,
76
+ "mask_channel_min_space": 1,
77
+ "mask_channel_other": 0.0,
78
+ "mask_channel_prob": 0.0,
79
+ "mask_channel_selection": "static",
80
+ "mask_feature_length": 10,
81
+ "mask_feature_min_masks": 0,
82
+ "mask_feature_prob": 0.0,
83
+ "mask_time_length": 10,
84
+ "mask_time_min_masks": 2,
85
+ "mask_time_min_space": 1,
86
+ "mask_time_other": 0.0,
87
+ "mask_time_prob": 0.05,
88
+ "mask_time_selection": "static",
89
+ "model_type": "wav2vec2",
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": 69,
101
+ "proj_codevector_dim": 768,
102
+ "tdnn_dilation": [
103
+ 1,
104
+ 2,
105
+ 3,
106
+ 1,
107
+ 1
108
+ ],
109
+ "tdnn_dim": [
110
+ 512,
111
+ 512,
112
+ 512,
113
+ 512,
114
+ 1500
115
+ ],
116
+ "tdnn_kernel": [
117
+ 5,
118
+ 3,
119
+ 3,
120
+ 1,
121
+ 1
122
+ ],
123
+ "torch_dtype": "float32",
124
+ "transformers_version": "4.44.2",
125
+ "use_weighted_layer_sum": false,
126
+ "vocab_size": 70,
127
+ "xvector_output_dim": 512
128
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8418614f0170cafced89205d930fa2d8505d272c0599a1632407205c220d1ead
3
+ size 1262861360
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/Oct14_19-27-58_ba0c8d9a2d7c/events.out.tfevents.1728934081.ba0c8d9a2d7c.2094.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e1d0fe29c84d78cff05f32f538bfeda455899ad632a52fc2e8870074e088a1e
3
+ size 8448
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a954500d9cf6fedc6065a1210769e4123196e39bf78a6c4e425bcf9832731d44
3
+ size 5240