Hugging Face's logo

JovialValley
/
model_broadclass_onSet4

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Model card Files
xet
Metrics Community
1
JovialValley commited on
Commit
a393b4b
·
1 Parent(s): 56c16d5

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +108 -0
README.md ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ - wer
8
+ model-index:
9
+ - name: model_broadclass_onSet4
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
+ # model_broadclass_onSet4
17
+
18
+ This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.1340
21
+ - 0 Precision: 1.0
22
+ - 0 Recall: 0.9615
23
+ - 0 F1-score: 0.9804
24
+ - 0 Support: 26
25
+ - 1 Precision: 1.0
26
+ - 1 Recall: 1.0
27
+ - 1 F1-score: 1.0
28
+ - 1 Support: 32
29
+ - 2 Precision: 1.0
30
+ - 2 Recall: 0.9643
31
+ - 2 F1-score: 0.9818
32
+ - 2 Support: 28
33
+ - 3 Precision: 0.8462
34
+ - 3 Recall: 1.0
35
+ - 3 F1-score: 0.9167
36
+ - 3 Support: 11
37
+ - Accuracy: 0.9794
38
+ - Macro avg Precision: 0.9615
39
+ - Macro avg Recall: 0.9815
40
+ - Macro avg F1-score: 0.9697
41
+ - Macro avg Support: 97
42
+ - Weighted avg Precision: 0.9826
43
+ - Weighted avg Recall: 0.9794
44
+ - Weighted avg F1-score: 0.9800
45
+ - Weighted avg Support: 97
46
+ - Wer: 0.1098
47
+ - Mtrix: [[0, 1, 2, 3], [0, 25, 0, 0, 1], [1, 0, 32, 0, 0], [2, 0, 0, 27, 1], [3, 0, 0, 0, 11]]
48
+
49
+ ## Model description
50
+
51
+ More information needed
52
+
53
+ ## Intended uses & limitations
54
+
55
+ More information needed
56
+
57
+ ## Training and evaluation data
58
+
59
+ More information needed
60
+
61
+ ## Training procedure
62
+
63
+ ### Training hyperparameters
64
+
65
+ The following hyperparameters were used during training:
66
+ - learning_rate: 0.0003
67
+ - train_batch_size: 8
68
+ - eval_batch_size: 8
69
+ - seed: 42
70
+ - gradient_accumulation_steps: 2
71
+ - total_train_batch_size: 16
72
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
73
+ - lr_scheduler_type: linear
74
+ - lr_scheduler_warmup_steps: 200
75
+ - num_epochs: 80
76
+ - mixed_precision_training: Native AMP
77
+
78
+ ### Training results
79
+
80
+ | Training Loss | Epoch | Step | Validation Loss | 0 Precision | 0 Recall | 0 F1-score | 0 Support | 1 Precision | 1 Recall | 1 F1-score | 1 Support | 2 Precision | 2 Recall | 2 F1-score | 2 Support | 3 Precision | 3 Recall | 3 F1-score | 3 Support | Accuracy | Macro avg Precision | Macro avg Recall | Macro avg F1-score | Macro avg Support | Weighted avg Precision | Weighted avg Recall | Weighted avg F1-score | Weighted avg Support | Wer | Mtrix |
81
+ |:-------------:|:-----:|:----:|:---------------:|:-----------:|:--------:|:----------:|:---------:|:-----------:|:--------:|:----------:|:---------:|:-----------:|:--------:|:----------:|:---------:|:-----------:|:--------:|:----------:|:---------:|:--------:|:-------------------:|:----------------:|:------------------:|:-----------------:|:----------------------:|:-------------------:|:---------------------:|:--------------------:|:------:|:--------------------------------------------------------------------------------------:|
82
+ | 2.337 | 4.16 | 100 | 2.1761 | 0.2680 | 1.0 | 0.4228 | 26 | 0.0 | 0.0 | 0.0 | 32 | 0.0 | 0.0 | 0.0 | 28 | 0.0 | 0.0 | 0.0 | 11 | 0.2680 | 0.0670 | 0.25 | 0.1057 | 97 | 0.0718 | 0.2680 | 0.1133 | 97 | 0.9869 | [[0, 1, 2, 3], [0, 26, 0, 0, 0], [1, 32, 0, 0, 0], [2, 28, 0, 0, 0], [3, 11, 0, 0, 0]] |
83
+ | 2.2604 | 8.33 | 200 | 2.0783 | 0.2680 | 1.0 | 0.4228 | 26 | 0.0 | 0.0 | 0.0 | 32 | 0.0 | 0.0 | 0.0 | 28 | 0.0 | 0.0 | 0.0 | 11 | 0.2680 | 0.0670 | 0.25 | 0.1057 | 97 | 0.0718 | 0.2680 | 0.1133 | 97 | 0.9869 | [[0, 1, 2, 3], [0, 26, 0, 0, 0], [1, 32, 0, 0, 0], [2, 28, 0, 0, 0], [3, 11, 0, 0, 0]] |
84
+ | 1.9239 | 12.49 | 300 | 1.8395 | 0.2680 | 1.0 | 0.4228 | 26 | 0.0 | 0.0 | 0.0 | 32 | 0.0 | 0.0 | 0.0 | 28 | 0.0 | 0.0 | 0.0 | 11 | 0.2680 | 0.0670 | 0.25 | 0.1057 | 97 | 0.0718 | 0.2680 | 0.1133 | 97 | 0.9869 | [[0, 1, 2, 3], [0, 26, 0, 0, 0], [1, 32, 0, 0, 0], [2, 28, 0, 0, 0], [3, 11, 0, 0, 0]] |
85
+ | 1.7002 | 16.65 | 400 | 1.7194 | 0.2680 | 1.0 | 0.4228 | 26 | 0.0 | 0.0 | 0.0 | 32 | 0.0 | 0.0 | 0.0 | 28 | 0.0 | 0.0 | 0.0 | 11 | 0.2680 | 0.0670 | 0.25 | 0.1057 | 97 | 0.0718 | 0.2680 | 0.1133 | 97 | 0.9869 | [[0, 1, 2, 3], [0, 26, 0, 0, 0], [1, 32, 0, 0, 0], [2, 28, 0, 0, 0], [3, 11, 0, 0, 0]] |
86
+ | 1.611 | 20.82 | 500 | 1.5619 | 0.2680 | 1.0 | 0.4228 | 26 | 0.0 | 0.0 | 0.0 | 32 | 0.0 | 0.0 | 0.0 | 28 | 0.0 | 0.0 | 0.0 | 11 | 0.2680 | 0.0670 | 0.25 | 0.1057 | 97 | 0.0718 | 0.2680 | 0.1133 | 97 | 0.9869 | [[0, 1, 2, 3], [0, 26, 0, 0, 0], [1, 32, 0, 0, 0], [2, 28, 0, 0, 0], [3, 11, 0, 0, 0]] |
87
+ | 1.486 | 24.98 | 600 | 1.5283 | 0.2680 | 1.0 | 0.4228 | 26 | 0.0 | 0.0 | 0.0 | 32 | 0.0 | 0.0 | 0.0 | 28 | 0.0 | 0.0 | 0.0 | 11 | 0.2680 | 0.0670 | 0.25 | 0.1057 | 97 | 0.0718 | 0.2680 | 0.1133 | 97 | 0.9869 | [[0, 1, 2, 3], [0, 26, 0, 0, 0], [1, 32, 0, 0, 0], [2, 28, 0, 0, 0], [3, 11, 0, 0, 0]] |
88
+ | 1.6085 | 29.16 | 700 | 1.5041 | 0.2680 | 1.0 | 0.4228 | 26 | 0.0 | 0.0 | 0.0 | 32 | 0.0 | 0.0 | 0.0 | 28 | 0.0 | 0.0 | 0.0 | 11 | 0.2680 | 0.0670 | 0.25 | 0.1057 | 97 | 0.0718 | 0.2680 | 0.1133 | 97 | 0.9869 | [[0, 1, 2, 3], [0, 26, 0, 0, 0], [1, 32, 0, 0, 0], [2, 28, 0, 0, 0], [3, 11, 0, 0, 0]] |
89
+ | 1.5607 | 33.33 | 800 | 1.4456 | 0.2680 | 1.0 | 0.4228 | 26 | 0.0 | 0.0 | 0.0 | 32 | 0.0 | 0.0 | 0.0 | 28 | 0.0 | 0.0 | 0.0 | 11 | 0.2680 | 0.0670 | 0.25 | 0.1057 | 97 | 0.0718 | 0.2680 | 0.1133 | 97 | 0.9945 | [[0, 1, 2, 3], [0, 26, 0, 0, 0], [1, 32, 0, 0, 0], [2, 28, 0, 0, 0], [3, 11, 0, 0, 0]] |
90
+ | 1.3499 | 37.49 | 900 | 1.2898 | 0.2680 | 1.0 | 0.4228 | 26 | 0.0 | 0.0 | 0.0 | 32 | 0.0 | 0.0 | 0.0 | 28 | 0.0 | 0.0 | 0.0 | 11 | 0.2680 | 0.0670 | 0.25 | 0.1057 | 97 | 0.0718 | 0.2680 | 0.1133 | 97 | 0.9970 | [[0, 1, 2, 3], [0, 26, 0, 0, 0], [1, 32, 0, 0, 0], [2, 28, 0, 0, 0], [3, 11, 0, 0, 0]] |
91
+ | 0.9722 | 41.65 | 1000 | 0.9757 | 0.3133 | 1.0 | 0.4771 | 26 | 1.0 | 0.1562 | 0.2703 | 32 | 1.0 | 0.1786 | 0.3030 | 28 | 1.0 | 0.3636 | 0.5333 | 11 | 0.4124 | 0.8283 | 0.4246 | 0.3959 | 97 | 0.8159 | 0.4124 | 0.3650 | 97 | 0.9612 | [[0, 1, 2, 3], [0, 26, 0, 0, 0], [1, 27, 5, 0, 0], [2, 23, 0, 5, 0], [3, 7, 0, 0, 4]] |
92
+ | 0.9679 | 45.82 | 1100 | 0.9452 | 0.4333 | 1.0 | 0.6047 | 26 | 0.9630 | 0.8125 | 0.8814 | 32 | 1.0 | 0.3214 | 0.4865 | 28 | 1.0 | 0.0909 | 0.1667 | 11 | 0.6392 | 0.8491 | 0.5562 | 0.5348 | 97 | 0.8359 | 0.6392 | 0.6122 | 97 | 0.9406 | [[0, 1, 2, 3], [0, 26, 0, 0, 0], [1, 6, 26, 0, 0], [2, 18, 1, 9, 0], [3, 10, 0, 0, 1]] |
93
+ | 0.9206 | 49.98 | 1200 | 0.9031 | 0.5909 | 1.0 | 0.7429 | 26 | 1.0 | 0.9062 | 0.9508 | 32 | 1.0 | 0.7143 | 0.8333 | 28 | 1.0 | 0.3636 | 0.5333 | 11 | 0.8144 | 0.8977 | 0.7460 | 0.7651 | 97 | 0.8903 | 0.8144 | 0.8138 | 97 | 0.9250 | [[0, 1, 2, 3], [0, 26, 0, 0, 0], [1, 3, 29, 0, 0], [2, 8, 0, 20, 0], [3, 7, 0, 0, 4]] |
94
+ | 0.9223 | 54.16 | 1300 | 0.8607 | 0.8125 | 1.0 | 0.8966 | 26 | 1.0 | 0.875 | 0.9333 | 32 | 1.0 | 0.9643 | 0.9818 | 28 | 1.0 | 0.9091 | 0.9524 | 11 | 0.9381 | 0.9531 | 0.9371 | 0.9410 | 97 | 0.9497 | 0.9381 | 0.9396 | 97 | 0.9366 | [[0, 1, 2, 3], [0, 26, 0, 0, 0], [1, 4, 28, 0, 0], [2, 1, 0, 27, 0], [3, 1, 0, 0, 10]] |
95
+ | 0.8407 | 58.33 | 1400 | 0.8011 | 0.8929 | 0.9615 | 0.9259 | 26 | 1.0 | 0.9688 | 0.9841 | 32 | 1.0 | 0.8929 | 0.9434 | 28 | 0.8462 | 1.0 | 0.9167 | 11 | 0.9485 | 0.9348 | 0.9558 | 0.9425 | 97 | 0.9538 | 0.9485 | 0.9491 | 97 | 0.9381 | [[0, 1, 2, 3], [0, 25, 0, 0, 1], [1, 1, 31, 0, 0], [2, 2, 0, 25, 1], [3, 0, 0, 0, 11]] |
96
+ | 0.7359 | 62.49 | 1500 | 0.7210 | 0.8966 | 1.0 | 0.9455 | 26 | 1.0 | 0.9375 | 0.9677 | 32 | 1.0 | 0.9286 | 0.9630 | 28 | 0.9167 | 1.0 | 0.9565 | 11 | 0.9588 | 0.9533 | 0.9665 | 0.9582 | 97 | 0.9628 | 0.9588 | 0.9591 | 97 | 0.9220 | [[0, 1, 2, 3], [0, 26, 0, 0, 0], [1, 2, 30, 0, 0], [2, 1, 0, 26, 1], [3, 0, 0, 0, 11]] |
97
+ | 0.5479 | 66.65 | 1600 | 0.4813 | 1.0 | 1.0 | 1.0 | 26 | 1.0 | 1.0 | 1.0 | 32 | 1.0 | 0.9643 | 0.9818 | 28 | 0.9167 | 1.0 | 0.9565 | 11 | 0.9897 | 0.9792 | 0.9911 | 0.9846 | 97 | 0.9905 | 0.9897 | 0.9898 | 97 | 0.7447 | [[0, 1, 2, 3], [0, 26, 0, 0, 0], [1, 0, 32, 0, 0], [2, 0, 0, 27, 1], [3, 0, 0, 0, 11]] |
98
+ | 0.2617 | 70.82 | 1700 | 0.2138 | 1.0 | 1.0 | 1.0 | 26 | 1.0 | 1.0 | 1.0 | 32 | 1.0 | 0.9643 | 0.9818 | 28 | 0.9167 | 1.0 | 0.9565 | 11 | 0.9897 | 0.9792 | 0.9911 | 0.9846 | 97 | 0.9905 | 0.9897 | 0.9898 | 97 | 0.1692 | [[0, 1, 2, 3], [0, 26, 0, 0, 0], [1, 0, 32, 0, 0], [2, 0, 0, 27, 1], [3, 0, 0, 0, 11]] |
99
+ | 0.2186 | 74.98 | 1800 | 0.1412 | 1.0 | 1.0 | 1.0 | 26 | 1.0 | 1.0 | 1.0 | 32 | 1.0 | 0.9643 | 0.9818 | 28 | 0.9167 | 1.0 | 0.9565 | 11 | 0.9897 | 0.9792 | 0.9911 | 0.9846 | 97 | 0.9905 | 0.9897 | 0.9898 | 97 | 0.1269 | [[0, 1, 2, 3], [0, 26, 0, 0, 0], [1, 0, 32, 0, 0], [2, 0, 0, 27, 1], [3, 0, 0, 0, 11]] |
100
+ | 0.2303 | 79.16 | 1900 | 0.1344 | 1.0 | 0.9615 | 0.9804 | 26 | 1.0 | 1.0 | 1.0 | 32 | 1.0 | 0.9643 | 0.9818 | 28 | 0.8462 | 1.0 | 0.9167 | 11 | 0.9794 | 0.9615 | 0.9815 | 0.9697 | 97 | 0.9826 | 0.9794 | 0.9800 | 97 | 0.1113 | [[0, 1, 2, 3], [0, 25, 0, 0, 1], [1, 0, 32, 0, 0], [2, 0, 0, 27, 1], [3, 0, 0, 0, 11]] |
101
+
102
+
103
+ ### Framework versions
104
+
105
+ - Transformers 4.25.1
106
+ - Pytorch 1.13.0+cu116
107
+ - Datasets 2.8.0
108
+ - Tokenizers 0.13.2