lalok/gyeongsan_address_firestation_ko_14000hr_M
This model is a fine-tuned version of openai/whisper-medium on the lalok/gyeongsan_address_firestation_ko_14000hr dataset. It achieves the following results on the evaluation set:
- Loss: 0.2375
- Cer: 16.0569
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: 100
- training_steps: 10000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.2677 | 0.0908 | 5000 | 0.2662 | 17.8377 |
| 0.2062 | 0.1816 | 10000 | 0.2375 | 16.0569 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.2.2+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 8
Model tree for lalok/gyeongsan_address_firestation_ko_14000hr_M
Base model
openai/whisper-medium