metadata
language:
- ko
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- idiotDeveloper/vts_sample_data_1.0
model-index:
- name: vts_to_text_based_small_1.0
results: []
vts_to_text_based_small_1.0
This model is a fine-tuned version of openai/whisper-small on the idiotDeveloper/vts_sample_data_1.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0365
- Cer: 0.0
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 20
- training_steps: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.0588 | 25.0 | 25 | 0.0556 | 100.0 |
| 0.0352 | 50.0 | 50 | 0.0365 | 0.0 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.3.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1