hughlan1214 commited on
Commit
079656c
1 Parent(s): 78cd4f2

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
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": "sum",
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": 0.1,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.0,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.1,
59
+ "hidden_size": 1024,
60
+ "id2label": {
61
+ "0": "angry",
62
+ "1": "disgust",
63
+ "2": "fear",
64
+ "3": "happy",
65
+ "4": "neutral",
66
+ "5": "sad",
67
+ "6": "surprise"
68
+ },
69
+ "initializer_range": 0.02,
70
+ "intermediate_size": 4096,
71
+ "label2id": {
72
+ "angry": "0",
73
+ "disgust": "1",
74
+ "fear": "2",
75
+ "happy": "3",
76
+ "neutral": "4",
77
+ "sad": "5",
78
+ "surprise": "6"
79
+ },
80
+ "layer_norm_eps": 1e-05,
81
+ "layerdrop": 0.1,
82
+ "mask_channel_length": 10,
83
+ "mask_channel_min_space": 1,
84
+ "mask_channel_other": 0.0,
85
+ "mask_channel_prob": 0.0,
86
+ "mask_channel_selection": "static",
87
+ "mask_feature_length": 10,
88
+ "mask_feature_min_masks": 0,
89
+ "mask_feature_prob": 0.0,
90
+ "mask_time_length": 10,
91
+ "mask_time_min_masks": 2,
92
+ "mask_time_min_space": 1,
93
+ "mask_time_other": 0.0,
94
+ "mask_time_prob": 0.075,
95
+ "mask_time_selection": "static",
96
+ "model_type": "wav2vec2",
97
+ "num_adapter_layers": 3,
98
+ "num_attention_heads": 16,
99
+ "num_codevector_groups": 2,
100
+ "num_codevectors_per_group": 320,
101
+ "num_conv_pos_embedding_groups": 16,
102
+ "num_conv_pos_embeddings": 128,
103
+ "num_feat_extract_layers": 7,
104
+ "num_hidden_layers": 24,
105
+ "num_negatives": 100,
106
+ "output_hidden_size": 1024,
107
+ "pad_token_id": 0,
108
+ "proj_codevector_dim": 768,
109
+ "tdnn_dilation": [
110
+ 1,
111
+ 2,
112
+ 3,
113
+ 1,
114
+ 1
115
+ ],
116
+ "tdnn_dim": [
117
+ 512,
118
+ 512,
119
+ 512,
120
+ 512,
121
+ 1500
122
+ ],
123
+ "tdnn_kernel": [
124
+ 5,
125
+ 3,
126
+ 3,
127
+ 1,
128
+ 1
129
+ ],
130
+ "torch_dtype": "float32",
131
+ "transformers_version": "4.38.1",
132
+ "use_weighted_layer_sum": false,
133
+ "vocab_size": 32,
134
+ "xvector_output_dim": 512
135
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6c0d421915cd2b4ff4675b0aa78a2b3a42672abeecbd5cf2a9f0795cb04945a
3
+ size 1262864444
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,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b81ac8f682cfc34db8c53c267120abff81036358d63e6363670dfb98bc8daff
3
+ size 4856