<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
whisper-tiny-testing-vlsp-v3
This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4708
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: 0.0015
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- distributed_type: tpu
- num_devices: 8
- total_train_batch_size: 256
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7873 | 0.89 | 500 | 1.7211 |
| 1.327 | 1.79 | 1000 | 1.3023 |
| 1.0798 | 2.68 | 1500 | 1.0686 |
| 0.9022 | 3.58 | 2000 | 0.9110 |
| 0.7705 | 4.47 | 2500 | 0.7969 |
| 0.6637 | 5.37 | 3000 | 0.7032 |
| 0.5782 | 6.26 | 3500 | 0.6252 |
| 0.5074 | 7.16 | 4000 | 0.5576 |
| 0.4494 | 8.05 | 4500 | 0.5033 |
| 0.4069 | 8.94 | 5000 | 0.4708 |
Framework versions
- Transformers 4.27.2
- Pytorch 2.1.0a0+gitcc01568
- Datasets 2.12.0
- Tokenizers 0.13.3
