metadata
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-small-ger
results: []
whisper-small-ger
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3770
- Wer: 26.2540
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: 50
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.7151 | 0.07 | 200 | 0.6823 | 34.0413 |
| 0.5949 | 0.13 | 400 | 0.6183 | 40.4059 |
| 0.5127 | 0.2 | 600 | 0.5119 | 27.8722 |
| 0.4318 | 0.27 | 800 | 0.4223 | 26.6114 |
| 0.352 | 0.33 | 1000 | 0.3770 | 26.2540 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0