Hanhpt23/whisper-base-Encod-vietmed

openai/whisper-base

This model is a fine-tuned version of openai/whisper-base on the pphuc25/VietMed-split-8-2 dataset. It achieves the following results on the evaluation set:

• Loss: 0.6028
• Wer: 23.6903

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: 0.0001
• train_batch_size: 8
• 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: 50
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.6717	1.0	569	0.6778	31.9019
0.4003	2.0	1138	0.5956	27.1280
0.2279	3.0	1707	0.5805	23.7415
0.0875	4.0	2276	0.6028	23.6903

Framework versions

• Transformers 4.41.1
• Pytorch 2.3.0
• Datasets 2.19.1
• Tokenizers 0.19.1