Hugging Face's logo

steveway
/
wav2vec2-large-robust-12-ft-emotion-msp-dim_onnx

ONNX
Model card Files Community
steveway commited on
Commit
492c990
•
1 Parent(s): 5943184

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. wav2vec2-large-robust-12-ft-emotion-msp-dim.config +123 -0
  2. wav2vec2-large-robust-12-ft-emotion-msp-dim.feature +9 -0
  3. wav2vec2-large-robust-12-ft-emotion-msp-dim.onnx +3 -0
  4. wav2vec2-large-robust-12-ft-emotion-msp-dim.processor +21 -0
  5. wav2vec2-large-robust-12-ft-emotion-msp-dim.tokens +4 -0
  6. wav2vec2-large-robust-12-ft-emotion-msp-dim.yaml +10 -0
wav2vec2-large-robust-12-ft-emotion-msp-dim.config ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Wav2Vec2Config {
2
+ "_name_or_path": "audeering/wav2vec2-large-robust-12-ft-emotion-msp-dim",
3
+ "activation_dropout": 0.1,
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
+ "Wav2Vec2ForSpeechClassification"
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": 0.1,
56
+ "finetuning_task": "wav2vec2_reg",
57
+ "gradient_checkpointing": false,
58
+ "hidden_act": "gelu",
59
+ "hidden_dropout": 0.1,
60
+ "hidden_dropout_prob": 0.1,
61
+ "hidden_size": 1024,
62
+ "id2label": {
63
+ "0": "arousal",
64
+ "1": "dominance",
65
+ "2": "valence"
66
+ },
67
+ "initializer_range": 0.02,
68
+ "intermediate_size": 4096,
69
+ "label2id": {
70
+ "arousal": 0,
71
+ "dominance": 1,
72
+ "valence": 2
73
+ },
74
+ "layer_norm_eps": 1e-05,
75
+ "layerdrop": 0.1,
76
+ "mask_feature_length": 10,
77
+ "mask_feature_min_masks": 0,
78
+ "mask_feature_prob": 0.0,
79
+ "mask_time_length": 10,
80
+ "mask_time_min_masks": 2,
81
+ "mask_time_prob": 0.05,
82
+ "model_type": "wav2vec2",
83
+ "num_adapter_layers": 3,
84
+ "num_attention_heads": 16,
85
+ "num_codevector_groups": 2,
86
+ "num_codevectors_per_group": 320,
87
+ "num_conv_pos_embedding_groups": 16,
88
+ "num_conv_pos_embeddings": 128,
89
+ "num_feat_extract_layers": 7,
90
+ "num_hidden_layers": 12,
91
+ "num_negatives": 100,
92
+ "output_hidden_size": 1024,
93
+ "pad_token_id": 0,
94
+ "pooling_mode": "mean",
95
+ "problem_type": "regression",
96
+ "proj_codevector_dim": 768,
97
+ "tdnn_dilation": [
98
+ 1,
99
+ 2,
100
+ 3,
101
+ 1,
102
+ 1
103
+ ],
104
+ "tdnn_dim": [
105
+ 512,
106
+ 512,
107
+ 512,
108
+ 512,
109
+ 1500
110
+ ],
111
+ "tdnn_kernel": [
112
+ 5,
113
+ 3,
114
+ 3,
115
+ 1,
116
+ 1
117
+ ],
118
+ "torch_dtype": "float32",
119
+ "transformers_version": "4.41.0",
120
+ "use_weighted_layer_sum": false,
121
+ "vocab_size": null,
122
+ "xvector_output_dim": 512
123
+ }
wav2vec2-large-robust-12-ft-emotion-msp-dim.feature ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ Wav2Vec2FeatureExtractor {
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": true,
8
+ "sampling_rate": 16000
9
+ }
wav2vec2-large-robust-12-ft-emotion-msp-dim.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba86ebca4174bf036182063e09495f7d523b8924a1a9c621f3daa1a0ec0b3595
3
+ size 661664947
wav2vec2-large-robust-12-ft-emotion-msp-dim.processor ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Wav2Vec2Processor:
2
+ - feature_extractor: Wav2Vec2FeatureExtractor {
3
+ "do_normalize": true,
4
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
5
+ "feature_size": 1,
6
+ "padding_side": "right",
7
+ "padding_value": 0.0,
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
11
+
12
+ - tokenizer: Wav2Vec2CTCTokenizer(name_or_path='audeering/wav2vec2-large-robust-12-ft-emotion-msp-dim', vocab_size=0, model_max_length=1000000000000000019884624838656, is_fast=False, padding_side='right', truncation_side='right', special_tokens={'bos_token': '<s>', 'eos_token': '</s>', 'unk_token': '<unk>', 'pad_token': '<pad>'}, clean_up_tokenization_spaces=True), added_tokens_decoder={
13
+ 0: AddedToken("<s>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
14
+ 1: AddedToken("</s>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
15
+ 2: AddedToken("<unk>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
16
+ 3: AddedToken("<pad>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
17
+ }
18
+
19
+ {
20
+ "processor_class": "Wav2Vec2Processor"
21
+ }
wav2vec2-large-robust-12-ft-emotion-msp-dim.tokens ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ 0: <s>
2
+ 1: </s>
3
+ 2: <unk>
4
+ 3: <pad>
wav2vec2-large-robust-12-ft-emotion-msp-dim.yaml ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ feature_extractor: Wav2Vec2FeatureExtractor
2
+ labels:
3
+ 0: arousal
4
+ 1: dominance
5
+ 2: valence
6
+ model: EmotionModel
7
+ sampling_rate: 16000
8
+ shape:
9
+ - 1
10
+ - 320000