metadata
language:
- ko
license: apache-2.0
tags:
- hf-asr-leaderboard
- generated_from_trainer
base_model: openai/whisper-small
datasets:
- korean_samll_dataset2
model-index:
- name: korean-small_t3
results: []
korean-small_t3
This model is a fine-tuned version of openai/whisper-small on the korean_samll_dataset2 dataset. It achieves the following results on the evaluation set:
- eval_loss: 3.5461
- eval_cer: 235.5384
- eval_runtime: 128.8271
- eval_samples_per_second: 1.56
- eval_steps_per_second: 0.202
- step: 0
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: 3.0
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2