Whisper Small German SBB all SNR - v2
This model is a fine-tuned version of openai/whisper-small on the SBB Dataset 05.01.2023 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4018
- Wer: 0.1833
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-06
- train_batch_size: 64
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
2.6097 | 0.71 | 100 | 0.9753 | 0.7838 |
0.754 | 1.42 | 200 | 0.6018 | 0.6906 |
0.5414 | 2.13 | 300 | 0.4864 | 0.5149 |
0.4521 | 2.84 | 400 | 0.4234 | 0.2372 |
0.4131 | 3.55 | 500 | 0.4018 | 0.1833 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1
- Datasets 2.8.0
- Tokenizers 0.12.1
- Downloads last month
- 11
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.