<!-- 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-bud
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: 0.2981
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 |
|---|---|---|---|
| 1.6445 | 0.2 | 500 | 1.5676 |
| 1.2228 | 0.4 | 1000 | 1.1948 |
| 0.9879 | 0.61 | 1500 | 0.9511 |
| 0.8074 | 0.81 | 2000 | 0.7840 |
| 0.6706 | 1.01 | 2500 | 0.6490 |
| 0.5661 | 1.21 | 3000 | 0.5541 |
| 0.4764 | 1.41 | 3500 | 0.4599 |
| 0.4037 | 1.61 | 4000 | 0.3905 |
| 0.3445 | 1.82 | 4500 | 0.3342 |
| 0.2976 | 2.02 | 5000 | 0.2981 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.1.0a0+gitcc01568
- Datasets 2.12.0
- Tokenizers 0.13.3
