Whisper Small Korean
This model is a fine-tuned version of openai/whisper-base on the mozilla-foundation/common_voice_16_1 hi dataset. It achieves the following results on the evaluation set:
- Loss: 0.4670
- Wer: 26.2957
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: 12
- eval_batch_size: 6
- 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: 5000
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.2366 | 2.04 | 1000 | 0.4182 | 27.3008 |
0.0693 | 4.08 | 2000 | 0.4670 | 26.2957 |
0.0252 | 7.03 | 3000 | 0.5334 | 26.9174 |
0.0052 | 9.07 | 4000 | 0.6184 | 26.7869 |
0.0029 | 12.03 | 5000 | 0.6465 | 26.6853 |
Framework versions
- Transformers 4.39.0
- Pytorch 2.2.1+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 7
Finetuned from
Dataset used to train idiotDeveloper/fineTuning
Evaluation results
- Wer on mozilla-foundation/common_voice_16_1 hitest set self-reported26.296