<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
openai/whisper-medium.en
This model is a fine-tuned version of openai/whisper-medium.en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2960
- Wer: 10.3463
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.3449 | 0.12 | 500 | 0.2603 | 10.9738 |
0.3078 | 1.07 | 1000 | 0.2300 | 10.4144 |
0.0824 | 2.01 | 1500 | 0.2341 | 9.5919 |
0.1783 | 2.13 | 2000 | 0.2283 | 10.2529 |
0.0161 | 3.08 | 2500 | 0.2648 | 10.2387 |
0.0088 | 4.02 | 3000 | 0.2778 | 10.1778 |
0.0053 | 4.14 | 3500 | 0.2852 | 10.5260 |
0.0083 | 5.09 | 4000 | 0.2960 | 10.3463 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2