whisper-base-finetuned-500v2

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

• Loss: 1.0286
• Wer Ortho: 83.7838
• Wer: 83.7838

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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.0004	33.3333	100	1.0012	81.0811	81.0811
0.0001	66.6667	200	1.0110	78.3784	78.3784
0.0001	100.0	300	1.0186	78.3784	78.3784
0.0	133.3333	400	1.0241	81.0811	81.0811
0.0	166.6667	500	1.0286	83.7838	83.7838

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1