<!-- 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-v2
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: 2.4996
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: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8315 | 12.5 | 100 | 2.4987 |
| 1.9005 | 25.0 | 200 | 2.3833 |
| 1.3527 | 37.5 | 300 | 2.1773 |
| 0.9178 | 50.0 | 400 | 2.0985 |
| 0.5916 | 62.5 | 500 | 2.1320 |
| 0.3686 | 75.0 | 600 | 2.2154 |
| 0.2106 | 87.5 | 700 | 2.3202 |
| 0.1102 | 100.0 | 800 | 2.3632 |
| 0.0468 | 112.5 | 900 | 2.4495 |
| 0.0141 | 125.0 | 1000 | 2.4996 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.1.0a0+gitcc01568
- Datasets 2.12.0
- Tokenizers 0.13.3
