shg1 commited on
Commit
551a4b6
1 Parent(s): 260a48d

End of training

Browse files
Files changed (5) hide show
  1. README.md +82 -0
  2. config.json +110 -0
  3. preprocessor_config.json +9 -0
  4. pytorch_model.bin +3 -0
  5. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/wav2vec2-base-960h
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: wav2vec2-base-nsc-demo-4
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # wav2vec2-base-nsc-demo-4
17
+
18
+ This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.3016
21
+ - Wer: 0.1720
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5.9591386586384804e-05
41
+ - train_batch_size: 32
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 100
47
+ - num_epochs: 51
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
53
+ | 0.7542 | 2.27 | 50 | 0.3351 | 0.1948 |
54
+ | 0.3912 | 4.55 | 100 | 0.3016 | 0.1720 |
55
+ | 0.2497 | 6.82 | 150 | 0.3247 | 0.1757 |
56
+ | 0.201 | 9.09 | 200 | 0.3111 | 0.1728 |
57
+ | 0.1602 | 11.36 | 250 | 0.3259 | 0.1723 |
58
+ | 0.1334 | 13.64 | 300 | 0.3431 | 0.1765 |
59
+ | 0.1083 | 15.91 | 350 | 0.3413 | 0.1726 |
60
+ | 0.1114 | 18.18 | 400 | 0.4089 | 0.1768 |
61
+ | 0.0828 | 20.45 | 450 | 0.3531 | 0.1765 |
62
+ | 0.0926 | 22.73 | 500 | 0.3481 | 0.1755 |
63
+ | 0.093 | 25.0 | 550 | 0.3379 | 0.1742 |
64
+ | 0.0772 | 27.27 | 600 | 0.3628 | 0.1779 |
65
+ | 0.0701 | 29.55 | 650 | 0.3747 | 0.1773 |
66
+ | 0.0736 | 31.82 | 700 | 0.3834 | 0.1808 |
67
+ | 0.0607 | 34.09 | 750 | 0.3747 | 0.1742 |
68
+ | 0.0629 | 36.36 | 800 | 0.3683 | 0.1734 |
69
+ | 0.0713 | 38.64 | 850 | 0.3671 | 0.1744 |
70
+ | 0.0728 | 40.91 | 900 | 0.3632 | 0.1749 |
71
+ | 0.0696 | 43.18 | 950 | 0.3615 | 0.1731 |
72
+ | 0.0638 | 45.45 | 1000 | 0.3591 | 0.1755 |
73
+ | 0.0552 | 47.73 | 1050 | 0.3608 | 0.1779 |
74
+ | 0.0578 | 50.0 | 1100 | 0.3630 | 0.1752 |
75
+
76
+
77
+ ### Framework versions
78
+
79
+ - Transformers 4.33.0
80
+ - Pytorch 2.0.0
81
+ - Datasets 2.1.0
82
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base-960h",
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
+ "Wav2Vec2ForCTC"
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": "mean",
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_dropout": 0.0,
52
+ "feat_extract_norm": "group",
53
+ "feat_proj_dropout": 0.1,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.1,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.1,
59
+ "hidden_dropout_prob": 0.1,
60
+ "hidden_size": 768,
61
+ "initializer_range": 0.02,
62
+ "intermediate_size": 3072,
63
+ "layer_norm_eps": 1e-05,
64
+ "layerdrop": 0.1,
65
+ "mask_feature_length": 10,
66
+ "mask_feature_min_masks": 0,
67
+ "mask_feature_prob": 0.0,
68
+ "mask_time_length": 10,
69
+ "mask_time_min_masks": 2,
70
+ "mask_time_prob": 0.05,
71
+ "model_type": "wav2vec2",
72
+ "num_adapter_layers": 3,
73
+ "num_attention_heads": 12,
74
+ "num_codevector_groups": 2,
75
+ "num_codevectors_per_group": 320,
76
+ "num_conv_pos_embedding_groups": 16,
77
+ "num_conv_pos_embeddings": 128,
78
+ "num_feat_extract_layers": 7,
79
+ "num_hidden_layers": 12,
80
+ "num_negatives": 100,
81
+ "output_hidden_size": 768,
82
+ "pad_token_id": 0,
83
+ "proj_codevector_dim": 256,
84
+ "tdnn_dilation": [
85
+ 1,
86
+ 2,
87
+ 3,
88
+ 1,
89
+ 1
90
+ ],
91
+ "tdnn_dim": [
92
+ 512,
93
+ 512,
94
+ 512,
95
+ 512,
96
+ 1500
97
+ ],
98
+ "tdnn_kernel": [
99
+ 5,
100
+ 3,
101
+ 3,
102
+ 1,
103
+ 1
104
+ ],
105
+ "torch_dtype": "float32",
106
+ "transformers_version": "4.33.0",
107
+ "use_weighted_layer_sum": false,
108
+ "vocab_size": 32,
109
+ "xvector_output_dim": 512
110
+ }
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 sha256:426b3b842aa029dffecd242ba7cf58f4d2a34556c0e1325108fe71e119d2294b
3
+ size 377658785
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:927cc2129302129ae9b937f441e4977a3fb851a04e705ed929691e70d88a133e
3
+ size 4027