bhattasp/whisper-finetuned-all-3
This model is a fine-tuned version of openai/whisper-tiny on the atcosimm,AtCO2_UWB, Bial dataset. It achieves the following results on the evaluation set:
- Loss: 0.2626
- Wer: 13.3868
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 |
|---|---|---|---|---|
| 0.2357 | 1.0 | 991 | 0.3171 | 17.5090 |
| 0.139 | 2.0 | 1982 | 0.2580 | 13.1683 |
| 0.0553 | 3.0 | 2973 | 0.2496 | 13.4280 |
| 0.0201 | 4.0 | 3964 | 0.2564 | 12.1646 |
| 0.018 | 5.0 | 4955 | 0.2626 | 13.3868 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0
- Downloads last month
- 97
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for bhattasp/whisper-finetuned-all-3
Base model
openai/whisper-tiny