w_medium

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

• Loss: 0.7098
• Wer: 74.8294

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
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.7765	0.4548	1000	0.7543	130.5512
0.6989	0.9095	2000	0.6826	74.6797
0.4569	1.3643	3000	0.6605	80.5546
0.4813	1.8190	4000	0.6465	79.3330
0.3847	2.2738	5000	0.6780	73.8704
0.3865	2.7285	6000	0.6712	82.8552
0.2736	3.1833	7000	0.7016	75.8153
0.2428	3.6380	8000	0.7098	74.8294

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu118
• Datasets 3.0.0
• Tokenizers 0.19.1