README.md

metadata

language:
  - ko
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - DianaJin/krmodel
model-index:
  - name: jinkrsmodel
    results: []

jinkrsmodel

This model is a fine-tuned version of openai/whisper-medium on the DianaJin/krmodel dataset. It achieves the following results on the evaluation set:

• Loss: 1.1290
• Cer: 92.0690

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: 20
• training_steps: 160
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
2.1899	13.33	40	1.0819	153.1034
0.0027	26.67	80	1.0554	24.8276
0.0006	40.0	120	1.1173	39.3103
0.0004	53.33	160	1.1290	92.0690

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.1+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0