k-seungri/k_whisper_output

k-seungri/k_whisper_model

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

• Loss: 0.6590
• Cer: 53.0478

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
0.0002	142.86	1000	0.5964	16.9687
0.0001	285.71	2000	0.6299	16.6392
0.0001	428.57	3000	0.6459	17.1334
0.0001	571.43	4000	0.6590	53.0478

Framework versions

• Transformers 4.38.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1