<!-- 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. -->
AN_demo_v2
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3792
- Wer Ortho: 23.8944
- Wer: 18.9022
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: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
Training results
Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
---|---|---|---|---|---|
0.6122 | 0.05 | 100 | 0.6629 | 26.6227 | 21.4371 |
0.2959 | 0.09 | 200 | 0.4153 | 26.0069 | 20.7252 |
0.3019 | 0.14 | 300 | 0.3976 | 24.9762 | 19.9102 |
0.2674 | 0.18 | 400 | 0.3872 | 24.2108 | 19.3480 |
0.2821 | 0.23 | 500 | 0.3792 | 23.8944 | 18.9022 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1