<!-- 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. -->
home_workstation_ASR
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: 0.3540
- Wer Ortho: 20.1592
- Wer: 15.1297
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: 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: 4000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.232 | 0.9 | 1000 | 0.3209 | 21.7751 | 16.8164 |
| 0.1153 | 1.8 | 2000 | 0.3150 | 20.7647 | 15.7552 |
| 0.0653 | 2.7 | 3000 | 0.3327 | 20.2443 | 15.2927 |
| 0.032 | 3.6 | 4000 | 0.3540 | 20.1592 | 15.1297 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1
