Hugging Face's logo

makhataei
/
Wav2vec2-xlsr-Shemo-Ravdess-4EMO

Transformers
PyTorch
TensorBoard
wav2vec2
Speech-Emotion-Recognition
Generated from Trainer
Model card Files
xet
Metrics Community
makhataei commited on
Commit
a5eba4e
·
1 Parent(s): 45aa9b1

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +40 -31
README.md CHANGED
@@ -1,7 +1,6 @@
1
  ---
2
  license: apache-2.0
3
  tags:
4
- - Speech-Emotion-Recognition
5
  - generated_from_trainer
6
  metrics:
7
  - accuracy
@@ -15,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # Wav2vec2-xlsr-Shemo-Ravdess-4EMO
17
 
18
- This model is a fine-tuned version of [makhataei/Wav2vec2-xlsr-Shemo-Ravdess-4EMO](https://huggingface.co/makhataei/Wav2vec2-xlsr-Shemo-Ravdess-4EMO) on the minoosh/shEMO dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.7387
21
- - Accuracy: 0.7166
22
 
23
  ## Model description
24
 
@@ -37,7 +36,7 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 1e-07
41
  - train_batch_size: 4
42
  - eval_batch_size: 4
43
  - seed: 42
@@ -46,37 +45,47 @@ The following hyperparameters were used during training:
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_ratio: 0.1
49
- - num_epochs: 25
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
- | 0.6737 | 1.0 | 250 | 0.7384 | 0.7211 |
56
- | 0.6774 | 2.0 | 500 | 0.7384 | 0.7211 |
57
- | 0.629 | 3.0 | 750 | 0.7386 | 0.7211 |
58
- | 0.636 | 4.0 | 1000 | 0.7386 | 0.7211 |
59
- | 0.627 | 5.0 | 1250 | 0.7386 | 0.7211 |
60
- | 0.6489 | 6.0 | 1500 | 0.7387 | 0.7211 |
61
- | 0.6399 | 7.0 | 1750 | 0.7386 | 0.7188 |
62
- | 0.6458 | 8.0 | 2000 | 0.7387 | 0.7188 |
63
- | 0.6397 | 9.0 | 2250 | 0.7387 | 0.7188 |
64
- | 0.6625 | 10.0 | 2500 | 0.7387 | 0.7166 |
65
- | 0.6535 | 11.0 | 2750 | 0.7387 | 0.7166 |
66
- | 0.6339 | 12.0 | 3000 | 0.7387 | 0.7166 |
67
- | 0.6352 | 13.0 | 3250 | 0.7387 | 0.7166 |
68
- | 0.6545 | 14.0 | 3500 | 0.7387 | 0.7166 |
69
- | 0.6441 | 15.0 | 3750 | 0.7387 | 0.7166 |
70
- | 0.6468 | 16.0 | 4000 | 0.7387 | 0.7166 |
71
- | 0.6467 | 17.0 | 4250 | 0.7387 | 0.7166 |
72
- | 0.6452 | 18.0 | 4500 | 0.7387 | 0.7166 |
73
- | 0.626 | 19.0 | 4750 | 0.7387 | 0.7166 |
74
- | 0.6254 | 20.0 | 5000 | 0.7387 | 0.7166 |
75
- | 0.6732 | 21.0 | 5250 | 0.7387 | 0.7166 |
76
- | 0.6351 | 22.0 | 5500 | 0.7387 | 0.7166 |
77
- | 0.622 | 23.0 | 5750 | 0.7387 | 0.7166 |
78
- | 0.6451 | 24.0 | 6000 | 0.7387 | 0.7166 |
79
- | 0.6419 | 25.0 | 6250 | 0.7387 | 0.7166 |
 
 
 
 
 
 
 
 
 
 
80
 
81
 
82
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
  tags:
 
4
  - generated_from_trainer
5
  metrics:
6
  - accuracy
 
14
 
15
  # Wav2vec2-xlsr-Shemo-Ravdess-4EMO
16
 
17
+ This model is a fine-tuned version of [makhataei/Wav2vec2-xlsr-Shemo-Ravdess-4EMO](https://huggingface.co/makhataei/Wav2vec2-xlsr-Shemo-Ravdess-4EMO) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.9835
20
+ - Accuracy: 0.6190
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - learning_rate: 0.01
40
  - train_batch_size: 4
41
  - eval_batch_size: 4
42
  - seed: 42
 
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_ratio: 0.1
48
+ - num_epochs: 35
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | 0.7376 | 1.0 | 250 | 1.0100 | 0.6689 |
55
+ | 1.2733 | 2.0 | 500 | 1.3807 | 0.5850 |
56
+ | 1.7009 | 3.0 | 750 | 1.0024 | 0.5714 |
57
+ | 3.0069 | 4.0 | 1000 | 1.3598 | 0.4785 |
58
+ | 4.5511 | 5.0 | 1250 | 8.6658 | 0.3039 |
59
+ | 2.831 | 6.0 | 1500 | 2.8852 | 0.3469 |
60
+ | 2.3913 | 7.0 | 1750 | 2.0323 | 0.5782 |
61
+ | 2.2987 | 8.0 | 2000 | 1.9650 | 0.5306 |
62
+ | 2.0132 | 9.0 | 2250 | 1.6913 | 0.3878 |
63
+ | 1.8175 | 10.0 | 2500 | 1.5166 | 0.4989 |
64
+ | 1.859 | 11.0 | 2750 | 1.1817 | 0.5578 |
65
+ | 1.6033 | 12.0 | 3000 | 1.2075 | 0.6122 |
66
+ | 1.6519 | 13.0 | 3250 | 1.0996 | 0.5465 |
67
+ | 2.1858 | 14.0 | 3500 | 1.4274 | 0.5283 |
68
+ | 1.5728 | 15.0 | 3750 | 1.0764 | 0.6259 |
69
+ | 1.648 | 16.0 | 4000 | 1.6617 | 0.4218 |
70
+ | 1.4401 | 17.0 | 4250 | 1.4324 | 0.5896 |
71
+ | 1.3501 | 18.0 | 4500 | 1.0811 | 0.6054 |
72
+ | 1.6036 | 19.0 | 4750 | 2.1125 | 0.5896 |
73
+ | 1.3228 | 20.0 | 5000 | 1.8447 | 0.4785 |
74
+ | 1.3832 | 21.0 | 5250 | 0.9073 | 0.6213 |
75
+ | 1.1591 | 22.0 | 5500 | 1.1426 | 0.5374 |
76
+ | 1.2755 | 23.0 | 5750 | 2.2184 | 0.4263 |
77
+ | 1.2263 | 24.0 | 6000 | 1.2036 | 0.5714 |
78
+ | 1.0472 | 25.0 | 6250 | 1.6974 | 0.5578 |
79
+ | 1.0637 | 26.0 | 6500 | 0.9981 | 0.6825 |
80
+ | 1.0458 | 27.0 | 6750 | 1.3478 | 0.6122 |
81
+ | 1.045 | 28.0 | 7000 | 1.3582 | 0.5646 |
82
+ | 0.9352 | 29.0 | 7250 | 1.2475 | 0.5918 |
83
+ | 0.9601 | 30.0 | 7500 | 1.0625 | 0.6304 |
84
+ | 1.0385 | 31.0 | 7750 | 1.0208 | 0.6032 |
85
+ | 0.8867 | 32.0 | 8000 | 1.1003 | 0.6032 |
86
+ | 0.8324 | 33.0 | 8250 | 0.9172 | 0.6689 |
87
+ | 0.7943 | 34.0 | 8500 | 0.9540 | 0.6259 |
88
+ | 0.8031 | 35.0 | 8750 | 0.9835 | 0.6190 |
89
 
90
 
91
  ### Framework versions