<!-- 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. -->
base.en-cv3-new
This model is a fine-tuned version of openai/whisper-base.en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0043
- Wer: 2.2957
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: 8
- 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: 3000
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.3954 | 2.0 | 500 | 0.2481 | 11.8567 |
0.1192 | 4.0 | 1000 | 0.0609 | 3.7336 |
0.0315 | 6.0 | 1500 | 0.0163 | 2.8254 |
0.0088 | 8.0 | 2000 | 0.0073 | 2.5479 |
0.005 | 10.0 | 2500 | 0.0049 | 2.3209 |
0.0045 | 12.0 | 3000 | 0.0043 | 2.2957 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.0
- Datasets 2.12.0
- Tokenizers 0.13.3