metadata
language:
- ko
license: apache-2.0
tags:
- hf-asr-leaderboard
- generated_from_trainer
metrics:
- wer
base_model: openai/whisper-large-v3
model-index:
- name: whisper_finetune
results: []
whisper_finetune
This model is a fine-tuned version of openai/whisper-large-v3 on the aihub_100000 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4970
- Cer: 5.4843
- Wer: 22.9248
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-08
- train_batch_size: 16
- eval_batch_size: 16
- 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: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer | Wer |
|---|---|---|---|---|---|
| 0.9923 | 0.9 | 1000 | 0.5893 | 6.0827 | 25.3866 |
| 0.9389 | 1.79 | 2000 | 0.4970 | 5.4843 | 22.9248 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 1.14.0a0+410ce96
- Datasets 2.17.1
- Tokenizers 0.15.2