<!-- 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: 0.2994
- Wer: 9.7808
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 |
---|---|---|---|---|
0.235 | 0.12 | 500 | 0.2735 | 11.0733 |
0.1927 | 1.06 | 1000 | 0.2339 | 10.5575 |
0.1119 | 1.18 | 1500 | 0.2280 | 9.6803 |
0.0863 | 2.12 | 2000 | 0.2379 | 11.0621 |
0.0322 | 3.05 | 2500 | 0.2614 | 9.9920 |
0.0303 | 3.17 | 3000 | 0.2611 | 10.2742 |
0.0161 | 4.11 | 3500 | 0.2885 | 10.4722 |
0.0513 | 5.04 | 4000 | 0.2994 | 9.7808 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2