bhattasp/whisper-finetuned-atcosim
This model is a fine-tuned version of openai/whisper-tiny on the Atcosim dataset. It achieves the following results on the evaluation set:
- Loss: 0.0786
- Wer: 3.5200
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.1819 | 1.0 | 478 | 0.1961 | 11.3373 |
0.0533 | 2.0 | 956 | 0.0933 | 4.2664 |
0.0168 | 3.0 | 1434 | 0.0814 | 3.5818 |
0.0094 | 4.0 | 1912 | 0.0788 | 3.5598 |
0.0025 | 5.0 | 2390 | 0.0786 | 3.5200 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0
- Downloads last month
- 19
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for bhattasp/whisper-finetuned-atcosim
Base model
openai/whisper-tiny