sumukhshadakshari/whisper-finetuned-bial2
This model is a fine-tuned version of openai/whisper-tiny on the bial2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3229
- Wer: 31.7789
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 |
|---|---|---|---|---|
| 1.4255 | 1.0 | 257 | 1.3274 | 102.7404 |
| 0.5538 | 2.0 | 514 | 0.5221 | 44.0872 |
| 0.3054 | 3.0 | 771 | 0.3637 | 30.5956 |
| 0.202 | 4.0 | 1028 | 0.3305 | 28.6649 |
| 0.1601 | 5.0 | 1285 | 0.3229 | 31.7789 |
Framework versions
- Transformers 4.44.1
- Pytorch 2.4.1
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 75
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 sumukhshadakshari/whisper-finetuned-bial2
Base model
openai/whisper-tiny