Whisper Small Ger - Daniel Dumschat
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4140
- Wer: 41.8407
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.9164 | 0.01 | 20 | 0.5221 | 44.9371 |
| 0.3544 | 0.01 | 40 | 0.5360 | 45.7451 |
| 0.3331 | 0.02 | 60 | 0.4984 | 40.7108 |
| 0.3284 | 0.03 | 80 | 0.4430 | 42.5701 |
| 0.2753 | 0.03 | 100 | 0.4140 | 41.8407 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.2
- Datasets 2.16.1
- Tokenizers 0.15.0
- Downloads last month
- 2