metadata
base_model: openai/whisper-medium
datasets:
- aihub.or.kr
language:
- ko
license: apache-2.0
tags:
- hf-asr-leaderboard
- generated_from_trainer
model-index:
- name: new_model
results: []
new_model
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: 0.3286
- Cer: 4.9724
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 |
|---|---|---|---|---|
| 0.0 | 333.3333 | 1000 | 0.2826 | 3.8674 |
| 0.0 | 666.6667 | 2000 | 0.3079 | 4.9724 |
| 0.0 | 1000.0 | 3000 | 0.3227 | 4.9724 |
| 0.0 | 1333.3333 | 4000 | 0.3286 | 4.9724 |
Framework versions
- Transformers 4.43.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1