Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
SungBeom-whisper-small-ko-no-bg-v1
This model is a fine-tuned version of SungBeom/whisper-small-ko on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.2086
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-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.01
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.4362 | 142.8571 | 500 | 0.1993 |
| 6.0024 | 285.7143 | 1000 | 0.2035 |
| 5.6884 | 428.5714 | 1500 | 0.2067 |
| 5.5198 | 571.4286 | 2000 | 0.2086 |
| 5.3977 | 714.2857 | 2500 | 0.2095 |
| 5.3111 | 857.1429 | 3000 | 0.2094 |
| 5.2526 | 1000.0 | 3500 | 0.2091 |
| 5.2176 | 1142.8571 | 4000 | 0.2087 |
| 5.1912 | 1285.7143 | 4500 | 0.2086 |
| 5.1898 | 1428.5714 | 5000 | 0.2086 |
Framework versions
- PEFT 0.10.0
- Transformers 4.41.0.dev0
- Pytorch 2.2.2+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 0
Unable to determine this model’s pipeline type. Check the
docs
.