metadata
language:
- ko
license: apache-2.0
base_model: openai/whisper-base
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- potatoSeop/chimsuja_dataset
model-index:
- name: whisper-chimsuja-added
results: []
whisper-chimsuja-added
This model is a fine-tuned version of openai/whisper-base on the potatoSeop/chimsuja_dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.1292
- Cer: 4.5958
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: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.0215 | 4.03 | 5000 | 0.1357 | 4.5024 |
| 0.0032 | 8.06 | 10000 | 0.1292 | 4.5958 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0