metadata
base_model: mujadid-syahbana/whisper-small-qur-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: audioclass-whisper-percobaan1
results: []
audioclass-whisper-percobaan1
This model is a fine-tuned version of mujadid-syahbana/whisper-small-qur-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0711
- Accuracy: 0.9864
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.0043 | 1.0 | 124 | 1.8622 | 0.8186 |
| 0.8439 | 2.0 | 248 | 0.3895 | 0.9433 |
| 0.1972 | 3.0 | 372 | 0.1850 | 0.9637 |
| 0.077 | 4.0 | 496 | 0.1139 | 0.9751 |
| 0.0289 | 5.0 | 620 | 0.1153 | 0.9773 |
| 0.0172 | 6.0 | 744 | 0.0783 | 0.9841 |
| 0.0133 | 7.0 | 868 | 0.0711 | 0.9864 |
| 0.0116 | 8.0 | 992 | 0.0714 | 0.9841 |
| 0.0088 | 9.0 | 1116 | 0.0774 | 0.9819 |
| 0.0079 | 10.0 | 1240 | 0.0800 | 0.9819 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1