metadata
language:
- ko
license: apache-2.0
tags:
- hf-asr-leaderboard
- generated_from_trainer
base_model: openai/whisper-medium
datasets:
- aihub.or.kr
model-index:
- name: whisper_medium_ptt
results: []
whisper_medium_ptt
This model is a fine-tuned version of openai/whisper-medium on the telephone dataset. It achieves the following results on the evaluation set:
- Loss: 0.9243
- Cer: 20.6774
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: 4
- 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: 4000
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.0001 | 71.43 | 1000 | 0.8405 | 21.2121 |
| 0.0 | 142.86 | 2000 | 0.8907 | 20.4991 |
| 0.0 | 214.29 | 3000 | 0.9152 | 20.6774 |
| 0.0 | 285.71 | 4000 | 0.9243 | 20.6774 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2