whisper_finetuning_for_kr_call_voice
This model is a fine-tuned version of openai/whisper-base on the stt data dataset. It achieves the following results on the evaluation set:
- Loss: 1.1428
- Cer: 196.3801
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 | Cer |
|---|---|---|---|---|
| 0.0001 | 500.0 | 1000 | 1.0225 | 195.9276 |
| 0.0001 | 1000.0 | 2000 | 1.0854 | 195.9276 |
| 0.0 | 1500.0 | 3000 | 1.1157 | 195.9276 |
| 0.0 | 2000.0 | 4000 | 1.1428 | 196.3801 |
Framework versions
- Transformers 4.46.0.dev0
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.20.1
- Downloads last month
- 6
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for luxlike/repo_name
Base model
openai/whisper-base