<!-- 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-base-full-data-aug-v2
This model is a fine-tuned version of openai/whisper-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2464
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: 16
- eval_batch_size: 8
- seed: 42
- distributed_type: tpu
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 256
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5000
- training_steps: 63840
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4006 | 1.57 | 5000 | 0.6323 |
| 0.2901 | 3.13 | 10000 | 0.4845 |
| 0.2405 | 4.7 | 15000 | 0.4379 |
| 0.2114 | 6.27 | 20000 | 0.3892 |
| 0.1892 | 7.83 | 25000 | 0.3610 |
| 0.1638 | 9.4 | 30000 | 0.3343 |
| 0.154 | 10.97 | 35000 | 0.3186 |
| 0.1363 | 12.53 | 40000 | 0.2989 |
| 0.1216 | 14.1 | 45000 | 0.2848 |
| 0.1087 | 15.67 | 50000 | 0.2718 |
| 0.0984 | 17.23 | 55000 | 0.2576 |
| 0.0894 | 18.8 | 60000 | 0.2441 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.1.0a0+gitcc01568
- Datasets 2.13.1
- Tokenizers 0.13.3
