whisper_ami_finetuned
This model is a fine-tuned version of openai/whisper-medium on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0307
- Wer: 28.8275
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: 2
- eval_batch_size: 2
- 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 |
|---|---|---|---|---|
| 1.3847 | 1.0 | 649 | 0.7598 | 29.7442 |
| 0.6419 | 2.0 | 1298 | 0.7462 | 28.5128 |
| 0.4658 | 3.0 | 1947 | 0.7728 | 28.7454 |
| 0.154 | 4.0 | 2596 | 0.8675 | 29.2516 |
| 0.0852 | 5.0 | 3245 | 1.0307 | 28.8275 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2
- Downloads last month
- 4
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.