metadata
library_name: transformers
language:
- ko
license: apache-2.0
base_model: openai/whisper-base
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- hgc_voice_0827_r1_dataset_tags
model-index:
- name: hgc_voice_0827_r1_model_name
results: []
hgc_voice_0827_r1_model_name
This model is a fine-tuned version of openai/whisper-base on the hgc_voice_0827_r1_dataset dataset. It achieves the following results on the evaluation set:
- Loss: 1.2441
- Cer: 22.5806
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
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.0001 | 500.0 | 1000 | 1.2326 | 21.5054 |
| 0.0 | 1000.0 | 2000 | 1.2041 | 21.5054 |
| 0.0 | 1500.0 | 3000 | 1.2326 | 21.5054 |
| 0.0 | 2000.0 | 4000 | 1.2441 | 22.5806 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1