Hugging Face's logo

yujiepan
/
internal.wav2vec2-base-superb-ks-int8-structured64-quantize-feature-extractor

Audio Classification
Transformers
PyTorch
OpenVINO
wav2vec2
Generated from Trainer
Model card Files Community
1
yujiepan commited on
Commit
be33661
·
1 Parent(s): efc2c3d

upload model

Browse files
Files changed (11) hide show
  1. README.md +77 -0
  2. all_results.json +12 -0
  3. config.json +146 -0
  4. openvino_config.json +85 -0
  5. openvino_model.bin +3 -0
  6. openvino_model.xml +0 -0
  7. preprocessor_config.json +9 -0
  8. pytorch_model.bin +3 -0
  9. structured_sparsity.csv +73 -0
  10. trainer_state.json +0 -0
  11. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - audio-classification
5
+ - generated_from_trainer
6
+ datasets:
7
+ - superb
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: w2v2-ks-jpqd-quant-FE-finetuned-student
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # w2v2-ks-jpqd-quant-FE-finetuned-student
19
+
20
+ This model is a fine-tuned version of [anton-l/wav2vec2-base-ft-keyword-spotting](https://huggingface.co/anton-l/wav2vec2-base-ft-keyword-spotting) on the superb dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.0869
23
+ - Accuracy: 0.9794
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 7e-05
43
+ - train_batch_size: 32
44
+ - eval_batch_size: 32
45
+ - seed: 42
46
+ - gradient_accumulation_steps: 4
47
+ - total_train_batch_size: 128
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: linear
50
+ - lr_scheduler_warmup_ratio: 0.5
51
+ - num_epochs: 12.0
52
+ - mixed_precision_training: Native AMP
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
57
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
58
+ | 0.3477 | 1.0 | 399 | 0.1516 | 0.9637 |
59
+ | 5.5957 | 2.0 | 798 | 5.4798 | 0.9545 |
60
+ | 8.7806 | 3.0 | 1197 | 8.6491 | 0.9634 |
61
+ | 10.4524 | 4.0 | 1596 | 10.2701 | 0.9554 |
62
+ | 10.8964 | 5.0 | 1995 | 10.7809 | 0.9647 |
63
+ | 10.9322 | 6.0 | 2394 | 10.7806 | 0.9619 |
64
+ | 0.2389 | 7.0 | 2793 | 0.1148 | 0.9738 |
65
+ | 0.2522 | 8.0 | 3192 | 0.1013 | 0.9747 |
66
+ | 0.2213 | 9.0 | 3591 | 0.0983 | 0.9754 |
67
+ | 0.2053 | 10.0 | 3990 | 0.0934 | 0.9768 |
68
+ | 0.1543 | 11.0 | 4389 | 0.0875 | 0.9779 |
69
+ | 0.1836 | 12.0 | 4788 | 0.0869 | 0.9794 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.26.0
75
+ - Pytorch 1.13.1+cu116
76
+ - Datasets 2.8.0
77
+ - Tokenizers 0.13.2
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 12.0,
3
+ "eval_accuracy": 0.9794057075610474,
4
+ "eval_loss": 0.08688130974769592,
5
+ "eval_runtime": 80.7938,
6
+ "eval_samples_per_second": 84.14,
7
+ "eval_steps_per_second": 2.636,
8
+ "train_loss": 3.67681538981503,
9
+ "train_runtime": 15601.2245,
10
+ "train_samples_per_second": 39.3,
11
+ "train_steps_per_second": 0.307
12
+ }
config.json ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "anton-l/wav2vec2-base-ft-keyword-spotting",
3
+ "activation_dropout": 0.0,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "NNCFNetwork"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 256,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": false,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "sum",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": false,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_norm": "group",
51
+ "feat_proj_dropout": 0.1,
52
+ "feat_quantizer_dropout": 0.0,
53
+ "final_dropout": 0.0,
54
+ "finetuning_task": "audio-classification",
55
+ "freeze_feat_extract_train": true,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_size": 768,
59
+ "id2label": {
60
+ "0": "yes",
61
+ "1": "no",
62
+ "10": "_silence_",
63
+ "11": "_unknown_",
64
+ "2": "up",
65
+ "3": "down",
66
+ "4": "left",
67
+ "5": "right",
68
+ "6": "on",
69
+ "7": "off",
70
+ "8": "stop",
71
+ "9": "go"
72
+ },
73
+ "initializer_range": 0.02,
74
+ "intermediate_size": 3072,
75
+ "label2id": {
76
+ "_silence_": "10",
77
+ "_unknown_": "11",
78
+ "down": "3",
79
+ "go": "9",
80
+ "left": "4",
81
+ "no": "1",
82
+ "off": "7",
83
+ "on": "6",
84
+ "right": "5",
85
+ "stop": "8",
86
+ "up": "2",
87
+ "yes": "0"
88
+ },
89
+ "layer_norm_eps": 1e-05,
90
+ "layerdrop": 0.05,
91
+ "mask_channel_length": 10,
92
+ "mask_channel_min_space": 1,
93
+ "mask_channel_other": 0.0,
94
+ "mask_channel_prob": 0.0,
95
+ "mask_channel_selection": "static",
96
+ "mask_feature_length": 10,
97
+ "mask_feature_min_masks": 0,
98
+ "mask_feature_prob": 0.0,
99
+ "mask_time_length": 10,
100
+ "mask_time_min_masks": 2,
101
+ "mask_time_min_space": 1,
102
+ "mask_time_other": 0.0,
103
+ "mask_time_prob": 0.05,
104
+ "mask_time_selection": "static",
105
+ "model_type": "wav2vec2",
106
+ "no_mask_channel_overlap": false,
107
+ "no_mask_time_overlap": false,
108
+ "num_adapter_layers": 3,
109
+ "num_attention_heads": 12,
110
+ "num_codevector_groups": 2,
111
+ "num_codevectors_per_group": 320,
112
+ "num_conv_pos_embedding_groups": 16,
113
+ "num_conv_pos_embeddings": 128,
114
+ "num_feat_extract_layers": 7,
115
+ "num_hidden_layers": 12,
116
+ "num_negatives": 100,
117
+ "output_hidden_size": 768,
118
+ "pad_token_id": 0,
119
+ "proj_codevector_dim": 256,
120
+ "tdnn_dilation": [
121
+ 1,
122
+ 2,
123
+ 3,
124
+ 1,
125
+ 1
126
+ ],
127
+ "tdnn_dim": [
128
+ 512,
129
+ 512,
130
+ 512,
131
+ 512,
132
+ 1500
133
+ ],
134
+ "tdnn_kernel": [
135
+ 5,
136
+ 3,
137
+ 3,
138
+ 1,
139
+ 1
140
+ ],
141
+ "torch_dtype": "float32",
142
+ "transformers_version": "4.26.0",
143
+ "use_weighted_layer_sum": false,
144
+ "vocab_size": 32,
145
+ "xvector_output_dim": 512
146
+ }
openvino_config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "compression": [
3
+ {
4
+ "algorithm": "movement_sparsity",
5
+ "ignored_scopes": [
6
+ "{re}projector",
7
+ "{re}classifier",
8
+ "{re}feature_extractor",
9
+ "{re}feature_projection",
10
+ "{re}pos_conv_embed"
11
+ ],
12
+ "params": {
13
+ "enable_structured_masking": true,
14
+ "importance_regularization_factor": 0.04,
15
+ "warmup_end_epoch": 6,
16
+ "warmup_start_epoch": 1
17
+ },
18
+ "sparse_structure_by_scopes": [
19
+ {
20
+ "mode": "block",
21
+ "sparse_factors": [
22
+ 32,
23
+ 32
24
+ ],
25
+ "target_scopes": "{re}.*Wav2Vec2Attention.*"
26
+ },
27
+ {
28
+ "axis": 0,
29
+ "mode": "per_dim",
30
+ "target_scopes": "{re}.*intermediate_dense.*"
31
+ },
32
+ {
33
+ "axis": 1,
34
+ "mode": "per_dim",
35
+ "target_scopes": "{re}.*output_dense.*"
36
+ }
37
+ ]
38
+ },
39
+ {
40
+ "algorithm": "quantization",
41
+ "export_to_onnx_standard_ops": false,
42
+ "ignored_scopes": [
43
+ "{re}.*__add___[0-1]",
44
+ "{re}.*layer_norm_0"
45
+ ],
46
+ "initializer": {
47
+ "batchnorm_adaptation": {
48
+ "num_bn_adaptation_samples": 256
49
+ },
50
+ "range": {
51
+ "num_init_samples": 512,
52
+ "params": {
53
+ "max_percentile": 99.99,
54
+ "min_percentile": 0.01
55
+ },
56
+ "type": "percentile"
57
+ }
58
+ },
59
+ "overflow_fix": "disable",
60
+ "preset": "mixed",
61
+ "quantize_inputs": false,
62
+ "scope_overrides": {
63
+ "activations": {
64
+ "{re}.*matmul_0": {
65
+ "mode": "symmetric"
66
+ }
67
+ }
68
+ }
69
+ }
70
+ ],
71
+ "input_info": [
72
+ {
73
+ "keyword": "input_values",
74
+ "sample_size": [
75
+ 32,
76
+ 16000
77
+ ],
78
+ "type": "float"
79
+ }
80
+ ],
81
+ "log_dir": "/nvme2/yujiepan/workspace/jpqd-test/playground/optimum-playground/0314.example-rerun/logs/w2v2-ks-jpqd-quant-FE-finetuned-student",
82
+ "optimum_version": "1.6.3",
83
+ "save_onnx_model": false,
84
+ "transformers_version": "4.26.0"
85
+ }
openvino_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b5fae9bdf736c3ee6bd39c80e56c1238ec19b961a7adececd85b1817f0c63f4
3
+ size 40812072
openvino_model.xml ADDED
The diff for this file is too large to render. See raw diff
 
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 sha256:2ace00e4138f3d1f5e327fdf91995b30d7c4f8ff0123b607e3b3a94fd560d368
3
+ size 719847044
structured_sparsity.csv ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ,group_id,type,torch_module,weight_shape,pruned_weight_shape,bias_shape,pruned_bias_shape,head_or_channel_id_to_keep,module_node_name
2
+ 0,0,MHSA,nncf_module.wav2vec2.encoder.layers.0.attention.q_proj,"(768, 768)","(128, 768)","(768,)","(128,)","[4, 10]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[0]/Wav2Vec2Attention[attention]/NNCFLinear[q_proj]/linear_0
3
+ 1,0,MHSA,nncf_module.wav2vec2.encoder.layers.0.attention.k_proj,"(768, 768)","(128, 768)","(768,)","(128,)","[4, 10]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[0]/Wav2Vec2Attention[attention]/NNCFLinear[k_proj]/linear_0
4
+ 2,0,MHSA,nncf_module.wav2vec2.encoder.layers.0.attention.v_proj,"(768, 768)","(128, 768)","(768,)","(128,)","[4, 10]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[0]/Wav2Vec2Attention[attention]/NNCFLinear[v_proj]/linear_0
5
+ 3,0,MHSA,nncf_module.wav2vec2.encoder.layers.0.attention.out_proj,"(768, 768)","(768, 128)","(768,)","(768,)","[4, 10]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[0]/Wav2Vec2Attention[attention]/NNCFLinear[out_proj]/linear_0
6
+ 4,1,FF,nncf_module.wav2vec2.encoder.layers.0.feed_forward.intermediate_dense,"(3072, 768)","(1943, 768)","(3072,)","(1943,)",[1943 items],Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[0]/Wav2Vec2FeedForward[feed_forward]/NNCFLinear[intermediate_dense]/linear_0
7
+ 5,1,FF,nncf_module.wav2vec2.encoder.layers.0.feed_forward.output_dense,"(768, 3072)","(768, 1943)","(768,)","(768,)",[1943 items],Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[0]/Wav2Vec2FeedForward[feed_forward]/NNCFLinear[output_dense]/linear_0
8
+ 6,2,MHSA,nncf_module.wav2vec2.encoder.layers.1.attention.q_proj,"(768, 768)","(256, 768)","(768,)","(256,)","[0, 1, 3, 4]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[1]/Wav2Vec2Attention[attention]/NNCFLinear[q_proj]/linear_0
9
+ 7,2,MHSA,nncf_module.wav2vec2.encoder.layers.1.attention.k_proj,"(768, 768)","(256, 768)","(768,)","(256,)","[0, 1, 3, 4]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[1]/Wav2Vec2Attention[attention]/NNCFLinear[k_proj]/linear_0
10
+ 8,2,MHSA,nncf_module.wav2vec2.encoder.layers.1.attention.v_proj,"(768, 768)","(256, 768)","(768,)","(256,)","[0, 1, 3, 4]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[1]/Wav2Vec2Attention[attention]/NNCFLinear[v_proj]/linear_0
11
+ 9,2,MHSA,nncf_module.wav2vec2.encoder.layers.1.attention.out_proj,"(768, 768)","(768, 256)","(768,)","(768,)","[0, 1, 3, 4]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[1]/Wav2Vec2Attention[attention]/NNCFLinear[out_proj]/linear_0
12
+ 10,3,FF,nncf_module.wav2vec2.encoder.layers.1.feed_forward.intermediate_dense,"(3072, 768)","(1710, 768)","(3072,)","(1710,)",[1710 items],Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[1]/Wav2Vec2FeedForward[feed_forward]/NNCFLinear[intermediate_dense]/linear_0
13
+ 11,3,FF,nncf_module.wav2vec2.encoder.layers.1.feed_forward.output_dense,"(768, 3072)","(768, 1710)","(768,)","(768,)",[1710 items],Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[1]/Wav2Vec2FeedForward[feed_forward]/NNCFLinear[output_dense]/linear_0
14
+ 12,4,MHSA,nncf_module.wav2vec2.encoder.layers.2.attention.q_proj,"(768, 768)","(576, 768)","(768,)","(576,)","[0, 2, 4, 6, 7, 8, 9, 10, 11]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[2]/Wav2Vec2Attention[attention]/NNCFLinear[q_proj]/linear_0
15
+ 13,4,MHSA,nncf_module.wav2vec2.encoder.layers.2.attention.k_proj,"(768, 768)","(576, 768)","(768,)","(576,)","[0, 2, 4, 6, 7, 8, 9, 10, 11]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[2]/Wav2Vec2Attention[attention]/NNCFLinear[k_proj]/linear_0
16
+ 14,4,MHSA,nncf_module.wav2vec2.encoder.layers.2.attention.v_proj,"(768, 768)","(576, 768)","(768,)","(576,)","[0, 2, 4, 6, 7, 8, 9, 10, 11]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[2]/Wav2Vec2Attention[attention]/NNCFLinear[v_proj]/linear_0
17
+ 15,4,MHSA,nncf_module.wav2vec2.encoder.layers.2.attention.out_proj,"(768, 768)","(768, 576)","(768,)","(768,)","[0, 2, 4, 6, 7, 8, 9, 10, 11]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[2]/Wav2Vec2Attention[attention]/NNCFLinear[out_proj]/linear_0
18
+ 16,5,FF,nncf_module.wav2vec2.encoder.layers.2.feed_forward.intermediate_dense,"(3072, 768)","(1621, 768)","(3072,)","(1621,)",[1621 items],Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[2]/Wav2Vec2FeedForward[feed_forward]/NNCFLinear[intermediate_dense]/linear_0
19
+ 17,5,FF,nncf_module.wav2vec2.encoder.layers.2.feed_forward.output_dense,"(768, 3072)","(768, 1621)","(768,)","(768,)",[1621 items],Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[2]/Wav2Vec2FeedForward[feed_forward]/NNCFLinear[output_dense]/linear_0
20
+ 18,6,MHSA,nncf_module.wav2vec2.encoder.layers.3.attention.q_proj,"(768, 768)","(192, 768)","(768,)","(192,)","[2, 4, 5]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[3]/Wav2Vec2Attention[attention]/NNCFLinear[q_proj]/linear_0
21
+ 19,6,MHSA,nncf_module.wav2vec2.encoder.layers.3.attention.k_proj,"(768, 768)","(192, 768)","(768,)","(192,)","[2, 4, 5]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[3]/Wav2Vec2Attention[attention]/NNCFLinear[k_proj]/linear_0
22
+ 20,6,MHSA,nncf_module.wav2vec2.encoder.layers.3.attention.v_proj,"(768, 768)","(192, 768)","(768,)","(192,)","[2, 4, 5]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[3]/Wav2Vec2Attention[attention]/NNCFLinear[v_proj]/linear_0
23
+ 21,6,MHSA,nncf_module.wav2vec2.encoder.layers.3.attention.out_proj,"(768, 768)","(768, 192)","(768,)","(768,)","[2, 4, 5]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[3]/Wav2Vec2Attention[attention]/NNCFLinear[out_proj]/linear_0
24
+ 22,7,FF,nncf_module.wav2vec2.encoder.layers.3.feed_forward.intermediate_dense,"(3072, 768)","(1555, 768)","(3072,)","(1555,)",[1555 items],Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[3]/Wav2Vec2FeedForward[feed_forward]/NNCFLinear[intermediate_dense]/linear_0
25
+ 23,7,FF,nncf_module.wav2vec2.encoder.layers.3.feed_forward.output_dense,"(768, 3072)","(768, 1555)","(768,)","(768,)",[1555 items],Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[3]/Wav2Vec2FeedForward[feed_forward]/NNCFLinear[output_dense]/linear_0
26
+ 24,8,MHSA,nncf_module.wav2vec2.encoder.layers.4.attention.q_proj,"(768, 768)","(192, 768)","(768,)","(192,)","[1, 2, 4]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[4]/Wav2Vec2Attention[attention]/NNCFLinear[q_proj]/linear_0
27
+ 25,8,MHSA,nncf_module.wav2vec2.encoder.layers.4.attention.k_proj,"(768, 768)","(192, 768)","(768,)","(192,)","[1, 2, 4]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[4]/Wav2Vec2Attention[attention]/NNCFLinear[k_proj]/linear_0
28
+ 26,8,MHSA,nncf_module.wav2vec2.encoder.layers.4.attention.v_proj,"(768, 768)","(192, 768)","(768,)","(192,)","[1, 2, 4]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[4]/Wav2Vec2Attention[attention]/NNCFLinear[v_proj]/linear_0
29
+ 27,8,MHSA,nncf_module.wav2vec2.encoder.layers.4.attention.out_proj,"(768, 768)","(768, 192)","(768,)","(768,)","[1, 2, 4]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[4]/Wav2Vec2Attention[attention]/NNCFLinear[out_proj]/linear_0
30
+ 28,9,FF,nncf_module.wav2vec2.encoder.layers.4.feed_forward.intermediate_dense,"(3072, 768)","(1330, 768)","(3072,)","(1330,)",[1330 items],Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[4]/Wav2Vec2FeedForward[feed_forward]/NNCFLinear[intermediate_dense]/linear_0
31
+ 29,9,FF,nncf_module.wav2vec2.encoder.layers.4.feed_forward.output_dense,"(768, 3072)","(768, 1330)","(768,)","(768,)",[1330 items],Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[4]/Wav2Vec2FeedForward[feed_forward]/NNCFLinear[output_dense]/linear_0
32
+ 30,10,MHSA,nncf_module.wav2vec2.encoder.layers.5.attention.q_proj,"(768, 768)","(128, 768)","(768,)","(128,)","[9, 10]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[5]/Wav2Vec2Attention[attention]/NNCFLinear[q_proj]/linear_0
33
+ 31,10,MHSA,nncf_module.wav2vec2.encoder.layers.5.attention.k_proj,"(768, 768)","(128, 768)","(768,)","(128,)","[9, 10]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[5]/Wav2Vec2Attention[attention]/NNCFLinear[k_proj]/linear_0
34
+ 32,10,MHSA,nncf_module.wav2vec2.encoder.layers.5.attention.v_proj,"(768, 768)","(128, 768)","(768,)","(128,)","[9, 10]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[5]/Wav2Vec2Attention[attention]/NNCFLinear[v_proj]/linear_0
35
+ 33,10,MHSA,nncf_module.wav2vec2.encoder.layers.5.attention.out_proj,"(768, 768)","(768, 128)","(768,)","(768,)","[9, 10]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[5]/Wav2Vec2Attention[attention]/NNCFLinear[out_proj]/linear_0
36
+ 34,11,FF,nncf_module.wav2vec2.encoder.layers.5.feed_forward.intermediate_dense,"(3072, 768)","(1059, 768)","(3072,)","(1059,)",[1059 items],Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[5]/Wav2Vec2FeedForward[feed_forward]/NNCFLinear[intermediate_dense]/linear_0
37
+ 35,11,FF,nncf_module.wav2vec2.encoder.layers.5.feed_forward.output_dense,"(768, 3072)","(768, 1059)","(768,)","(768,)",[1059 items],Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[5]/Wav2Vec2FeedForward[feed_forward]/NNCFLinear[output_dense]/linear_0
38
+ 36,12,MHSA,nncf_module.wav2vec2.encoder.layers.6.attention.q_proj,"(768, 768)","(192, 768)","(768,)","(192,)","[1, 2, 5]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[6]/Wav2Vec2Attention[attention]/NNCFLinear[q_proj]/linear_0
39
+ 37,12,MHSA,nncf_module.wav2vec2.encoder.layers.6.attention.k_proj,"(768, 768)","(192, 768)","(768,)","(192,)","[1, 2, 5]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[6]/Wav2Vec2Attention[attention]/NNCFLinear[k_proj]/linear_0
40
+ 38,12,MHSA,nncf_module.wav2vec2.encoder.layers.6.attention.v_proj,"(768, 768)","(192, 768)","(768,)","(192,)","[1, 2, 5]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[6]/Wav2Vec2Attention[attention]/NNCFLinear[v_proj]/linear_0
41
+ 39,12,MHSA,nncf_module.wav2vec2.encoder.layers.6.attention.out_proj,"(768, 768)","(768, 192)","(768,)","(768,)","[1, 2, 5]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[6]/Wav2Vec2Attention[attention]/NNCFLinear[out_proj]/linear_0
42
+ 40,13,FF,nncf_module.wav2vec2.encoder.layers.6.feed_forward.intermediate_dense,"(3072, 768)","(871, 768)","(3072,)","(871,)",[871 items],Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[6]/Wav2Vec2FeedForward[feed_forward]/NNCFLinear[intermediate_dense]/linear_0
43
+ 41,13,FF,nncf_module.wav2vec2.encoder.layers.6.feed_forward.output_dense,"(768, 3072)","(768, 871)","(768,)","(768,)",[871 items],Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[6]/Wav2Vec2FeedForward[feed_forward]/NNCFLinear[output_dense]/linear_0
44
+ 42,14,MHSA,nncf_module.wav2vec2.encoder.layers.7.attention.q_proj,"(768, 768)","(384, 768)","(768,)","(384,)","[0, 2, 6, 7, 10, 11]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[7]/Wav2Vec2Attention[attention]/NNCFLinear[q_proj]/linear_0
45
+ 43,14,MHSA,nncf_module.wav2vec2.encoder.layers.7.attention.k_proj,"(768, 768)","(384, 768)","(768,)","(384,)","[0, 2, 6, 7, 10, 11]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[7]/Wav2Vec2Attention[attention]/NNCFLinear[k_proj]/linear_0
46
+ 44,14,MHSA,nncf_module.wav2vec2.encoder.layers.7.attention.v_proj,"(768, 768)","(384, 768)","(768,)","(384,)","[0, 2, 6, 7, 10, 11]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[7]/Wav2Vec2Attention[attention]/NNCFLinear[v_proj]/linear_0
47
+ 45,14,MHSA,nncf_module.wav2vec2.encoder.layers.7.attention.out_proj,"(768, 768)","(768, 384)","(768,)","(768,)","[0, 2, 6, 7, 10, 11]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[7]/Wav2Vec2Attention[attention]/NNCFLinear[out_proj]/linear_0
48
+ 46,15,FF,nncf_module.wav2vec2.encoder.layers.7.feed_forward.intermediate_dense,"(3072, 768)","(735, 768)","(3072,)","(735,)",[735 items],Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[7]/Wav2Vec2FeedForward[feed_forward]/NNCFLinear[intermediate_dense]/linear_0
49
+ 47,15,FF,nncf_module.wav2vec2.encoder.layers.7.feed_forward.output_dense,"(768, 3072)","(768, 735)","(768,)","(768,)",[735 items],Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[7]/Wav2Vec2FeedForward[feed_forward]/NNCFLinear[output_dense]/linear_0
50
+ 48,16,MHSA,nncf_module.wav2vec2.encoder.layers.8.attention.q_proj,"(768, 768)","(128, 768)","(768,)","(128,)","[5, 7]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[8]/Wav2Vec2Attention[attention]/NNCFLinear[q_proj]/linear_0
51
+ 49,16,MHSA,nncf_module.wav2vec2.encoder.layers.8.attention.k_proj,"(768, 768)","(128, 768)","(768,)","(128,)","[5, 7]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[8]/Wav2Vec2Attention[attention]/NNCFLinear[k_proj]/linear_0
52
+ 50,16,MHSA,nncf_module.wav2vec2.encoder.layers.8.attention.v_proj,"(768, 768)","(128, 768)","(768,)","(128,)","[5, 7]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[8]/Wav2Vec2Attention[attention]/NNCFLinear[v_proj]/linear_0
53
+ 51,16,MHSA,nncf_module.wav2vec2.encoder.layers.8.attention.out_proj,"(768, 768)","(768, 128)","(768,)","(768,)","[5, 7]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[8]/Wav2Vec2Attention[attention]/NNCFLinear[out_proj]/linear_0
54
+ 52,17,FF,nncf_module.wav2vec2.encoder.layers.8.feed_forward.intermediate_dense,"(3072, 768)","(857, 768)","(3072,)","(857,)",[857 items],Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[8]/Wav2Vec2FeedForward[feed_forward]/NNCFLinear[intermediate_dense]/linear_0
55
+ 53,17,FF,nncf_module.wav2vec2.encoder.layers.8.feed_forward.output_dense,"(768, 3072)","(768, 857)","(768,)","(768,)",[857 items],Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[8]/Wav2Vec2FeedForward[feed_forward]/NNCFLinear[output_dense]/linear_0
56
+ 54,18,MHSA,nncf_module.wav2vec2.encoder.layers.9.attention.q_proj,"(768, 768)","(320, 768)","(768,)","(320,)","[0, 1, 2, 5, 8]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[9]/Wav2Vec2Attention[attention]/NNCFLinear[q_proj]/linear_0
57
+ 55,18,MHSA,nncf_module.wav2vec2.encoder.layers.9.attention.k_proj,"(768, 768)","(320, 768)","(768,)","(320,)","[0, 1, 2, 5, 8]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[9]/Wav2Vec2Attention[attention]/NNCFLinear[k_proj]/linear_0
58
+ 56,18,MHSA,nncf_module.wav2vec2.encoder.layers.9.attention.v_proj,"(768, 768)","(320, 768)","(768,)","(320,)","[0, 1, 2, 5, 8]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[9]/Wav2Vec2Attention[attention]/NNCFLinear[v_proj]/linear_0
59
+ 57,18,MHSA,nncf_module.wav2vec2.encoder.layers.9.attention.out_proj,"(768, 768)","(768, 320)","(768,)","(768,)","[0, 1, 2, 5, 8]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[9]/Wav2Vec2Attention[attention]/NNCFLinear[out_proj]/linear_0
60
+ 58,19,FF,nncf_module.wav2vec2.encoder.layers.9.feed_forward.intermediate_dense,"(3072, 768)","(1110, 768)","(3072,)","(1110,)",[1110 items],Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[9]/Wav2Vec2FeedForward[feed_forward]/NNCFLinear[intermediate_dense]/linear_0
61
+ 59,19,FF,nncf_module.wav2vec2.encoder.layers.9.feed_forward.output_dense,"(768, 3072)","(768, 1110)","(768,)","(768,)",[1110 items],Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[9]/Wav2Vec2FeedForward[feed_forward]/NNCFLinear[output_dense]/linear_0
62
+ 60,20,MHSA,nncf_module.wav2vec2.encoder.layers.10.attention.q_proj,"(768, 768)","(128, 768)","(768,)","(128,)","[8, 11]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[10]/Wav2Vec2Attention[attention]/NNCFLinear[q_proj]/linear_0
63
+ 61,20,MHSA,nncf_module.wav2vec2.encoder.layers.10.attention.k_proj,"(768, 768)","(128, 768)","(768,)","(128,)","[8, 11]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[10]/Wav2Vec2Attention[attention]/NNCFLinear[k_proj]/linear_0
64
+ 62,20,MHSA,nncf_module.wav2vec2.encoder.layers.10.attention.v_proj,"(768, 768)","(128, 768)","(768,)","(128,)","[8, 11]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[10]/Wav2Vec2Attention[attention]/NNCFLinear[v_proj]/linear_0
65
+ 63,20,MHSA,nncf_module.wav2vec2.encoder.layers.10.attention.out_proj,"(768, 768)","(768, 128)","(768,)","(768,)","[8, 11]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[10]/Wav2Vec2Attention[attention]/NNCFLinear[out_proj]/linear_0
66
+ 64,21,FF,nncf_module.wav2vec2.encoder.layers.10.feed_forward.intermediate_dense,"(3072, 768)","(1042, 768)","(3072,)","(1042,)",[1042 items],Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[10]/Wav2Vec2FeedForward[feed_forward]/NNCFLinear[intermediate_dense]/linear_0
67
+ 65,21,FF,nncf_module.wav2vec2.encoder.layers.10.feed_forward.output_dense,"(768, 3072)","(768, 1042)","(768,)","(768,)",[1042 items],Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[10]/Wav2Vec2FeedForward[feed_forward]/NNCFLinear[output_dense]/linear_0
68
+ 66,22,MHSA,nncf_module.wav2vec2.encoder.layers.11.attention.q_proj,"(768, 768)","(192, 768)","(768,)","(192,)","[2, 4, 6]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[11]/Wav2Vec2Attention[attention]/NNCFLinear[q_proj]/linear_0
69
+ 67,22,MHSA,nncf_module.wav2vec2.encoder.layers.11.attention.k_proj,"(768, 768)","(192, 768)","(768,)","(192,)","[2, 4, 6]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[11]/Wav2Vec2Attention[attention]/NNCFLinear[k_proj]/linear_0
70
+ 68,22,MHSA,nncf_module.wav2vec2.encoder.layers.11.attention.v_proj,"(768, 768)","(192, 768)","(768,)","(192,)","[2, 4, 6]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[11]/Wav2Vec2Attention[attention]/NNCFLinear[v_proj]/linear_0
71
+ 69,22,MHSA,nncf_module.wav2vec2.encoder.layers.11.attention.out_proj,"(768, 768)","(768, 192)","(768,)","(768,)","[2, 4, 6]",Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[11]/Wav2Vec2Attention[attention]/NNCFLinear[out_proj]/linear_0
72
+ 70,23,FF,nncf_module.wav2vec2.encoder.layers.11.feed_forward.intermediate_dense,"(3072, 768)","(573, 768)","(3072,)","(573,)",[573 items],Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[11]/Wav2Vec2FeedForward[feed_forward]/NNCFLinear[intermediate_dense]/linear_0
73
+ 71,23,FF,nncf_module.wav2vec2.encoder.layers.11.feed_forward.output_dense,"(768, 3072)","(768, 573)","(768,)","(768,)",[573 items],Wav2Vec2ForSequenceClassification/Wav2Vec2Model[wav2vec2]/Wav2Vec2Encoder[encoder]/ModuleList[layers]/Wav2Vec2EncoderLayer[11]/Wav2Vec2FeedForward[feed_forward]/NNCFLinear[output_dense]/linear_0
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f34bbb355269549544bd2b53e9d4ef05446fb4d8a782e1c51eed15257eb88fe
3
+ size 3899