<!-- 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. -->
v4
This model is a fine-tuned version of openai/whisper-medium on the childes dataset. It achieves the following results on the evaluation set:
- Loss: 0.4543
- Wer: 29.6250
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: 1e-05
- train_batch_size: 16
- 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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0679 | 2.05 | 1000 | 0.3421 | 25.1885 |
| 0.0187 | 4.11 | 2000 | 0.4067 | 25.3238 |
| 0.0045 | 6.16 | 3000 | 0.4340 | 25.5848 |
| 0.0006 | 8.21 | 4000 | 0.4543 | 29.6250 |
Framework versions
- Transformers 4.28.0
- Pytorch 1.13.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
