Hanhpt23/whisper-tiny-smmmu
This model is a fine-tuned version of Hanhpt23/whisper-tiny-smmmu on the Hanhpt23/SLISA dataset. It achieves the following results on the evaluation set:
- Loss: 0.0002
- Wer: 0.0
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0873 | 1.0 | 30 | 0.0128 | 0.2480 |
| 0.0156 | 2.0 | 60 | 0.0052 | 3.2398 |
| 0.0062 | 3.0 | 90 | 0.0070 | 0.1705 |
| 0.0101 | 4.0 | 120 | 0.0349 | 2.4027 |
| 0.0251 | 5.0 | 150 | 0.0085 | 0.2325 |
| 0.0124 | 6.0 | 180 | 0.0091 | 0.1860 |
| 0.016 | 7.0 | 210 | 0.0031 | 0.0465 |
| 0.0039 | 8.0 | 240 | 0.0020 | 0.0465 |
| 0.0044 | 9.0 | 270 | 0.0003 | 0.0155 |
| 0.0003 | 10.0 | 300 | 0.0002 | 0.0 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0
- Datasets 2.19.1
- Tokenizers 0.19.1