Commit
•
2add8d6
1
Parent(s):
426dc35
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: wav2vec2-xlsr-korean-speech-emotion-recognition2_data_rebalance
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# wav2vec2-xlsr-korean-speech-emotion-recognition2_data_rebalance
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [jungjongho/wav2vec2-large-xlsr-korean-demo-colab_epoch15](https://huggingface.co/jungjongho/wav2vec2-large-xlsr-korean-demo-colab_epoch15) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.0124
|
| 20 |
+
- Accuracy: 0.9976
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 0.0002
|
| 40 |
+
- train_batch_size: 2
|
| 41 |
+
- eval_batch_size: 2
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 2
|
| 44 |
+
- total_train_batch_size: 4
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- num_epochs: 2
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 54 |
+
| 1.1219 | 0.04 | 200 | 1.4543 | 0.5792 |
|
| 55 |
+
| 0.7585 | 0.08 | 400 | 0.6959 | 0.7301 |
|
| 56 |
+
| 0.5959 | 0.13 | 600 | 0.7356 | 0.7671 |
|
| 57 |
+
| 0.4048 | 0.17 | 800 | 0.2661 | 0.9128 |
|
| 58 |
+
| 0.3101 | 0.21 | 1000 | 0.2470 | 0.9291 |
|
| 59 |
+
| 0.2805 | 0.25 | 1200 | 0.2115 | 0.9394 |
|
| 60 |
+
| 0.2885 | 0.29 | 1400 | 0.3597 | 0.9152 |
|
| 61 |
+
| 0.1703 | 0.33 | 1600 | 0.3973 | 0.9142 |
|
| 62 |
+
| 0.1818 | 0.38 | 1800 | 0.2164 | 0.9543 |
|
| 63 |
+
| 0.1727 | 0.42 | 2000 | 0.1133 | 0.9730 |
|
| 64 |
+
| 0.1038 | 0.46 | 2200 | 0.0826 | 0.9851 |
|
| 65 |
+
| 0.1343 | 0.5 | 2400 | 0.0823 | 0.9820 |
|
| 66 |
+
| 0.1412 | 0.54 | 2600 | 0.0762 | 0.9830 |
|
| 67 |
+
| 0.1321 | 0.58 | 2800 | 0.0786 | 0.9806 |
|
| 68 |
+
| 0.0738 | 0.63 | 3000 | 0.1036 | 0.9810 |
|
| 69 |
+
| 0.0998 | 0.67 | 3200 | 0.1984 | 0.9640 |
|
| 70 |
+
| 0.1135 | 0.71 | 3400 | 0.0775 | 0.9841 |
|
| 71 |
+
| 0.0552 | 0.75 | 3600 | 0.0923 | 0.9827 |
|
| 72 |
+
| 0.0633 | 0.79 | 3800 | 0.0518 | 0.9900 |
|
| 73 |
+
| 0.0769 | 0.83 | 4000 | 0.0599 | 0.9875 |
|
| 74 |
+
| 0.1026 | 0.88 | 4200 | 0.0800 | 0.9841 |
|
| 75 |
+
| 0.0641 | 0.92 | 4400 | 0.2396 | 0.9606 |
|
| 76 |
+
| 0.1068 | 0.96 | 4600 | 0.0653 | 0.9875 |
|
| 77 |
+
| 0.0802 | 1.0 | 4800 | 0.0844 | 0.9855 |
|
| 78 |
+
| 0.0483 | 1.04 | 5000 | 0.0984 | 0.9834 |
|
| 79 |
+
| 0.0392 | 1.09 | 5200 | 0.1092 | 0.9813 |
|
| 80 |
+
| 0.0408 | 1.13 | 5400 | 0.0719 | 0.9900 |
|
| 81 |
+
| 0.0388 | 1.17 | 5600 | 0.0494 | 0.9903 |
|
| 82 |
+
| 0.0253 | 1.21 | 5800 | 0.1486 | 0.9751 |
|
| 83 |
+
| 0.0448 | 1.25 | 6000 | 0.1370 | 0.9782 |
|
| 84 |
+
| 0.0415 | 1.29 | 6200 | 0.0508 | 0.9907 |
|
| 85 |
+
| 0.0552 | 1.34 | 6400 | 0.0332 | 0.9941 |
|
| 86 |
+
| 0.065 | 1.38 | 6600 | 0.0479 | 0.9900 |
|
| 87 |
+
| 0.0391 | 1.42 | 6800 | 0.0470 | 0.9910 |
|
| 88 |
+
| 0.0339 | 1.46 | 7000 | 0.0550 | 0.9886 |
|
| 89 |
+
| 0.0525 | 1.5 | 7200 | 0.0389 | 0.9920 |
|
| 90 |
+
| 0.0393 | 1.54 | 7400 | 0.0543 | 0.9910 |
|
| 91 |
+
| 0.0488 | 1.59 | 7600 | 0.0205 | 0.9965 |
|
| 92 |
+
| 0.0253 | 1.63 | 7800 | 0.0240 | 0.9948 |
|
| 93 |
+
| 0.0438 | 1.67 | 8000 | 0.0308 | 0.9952 |
|
| 94 |
+
| 0.0291 | 1.71 | 8200 | 0.0160 | 0.9969 |
|
| 95 |
+
| 0.0235 | 1.75 | 8400 | 0.0124 | 0.9969 |
|
| 96 |
+
| 0.0061 | 1.8 | 8600 | 0.0191 | 0.9962 |
|
| 97 |
+
| 0.022 | 1.84 | 8800 | 0.0178 | 0.9958 |
|
| 98 |
+
| 0.0176 | 1.88 | 9000 | 0.0135 | 0.9965 |
|
| 99 |
+
| 0.0168 | 1.92 | 9200 | 0.0161 | 0.9969 |
|
| 100 |
+
| 0.0068 | 1.96 | 9400 | 0.0124 | 0.9976 |
|
| 101 |
+
|
| 102 |
+
|
| 103 |
+
### Framework versions
|
| 104 |
+
|
| 105 |
+
- Transformers 4.22.0.dev0
|
| 106 |
+
- Pytorch 1.12.1+cu113
|
| 107 |
+
- Datasets 2.4.1.dev0
|
| 108 |
+
- Tokenizers 0.12.1
|