msc_imasc_openslr_festfox_Whisper_Medium_2_increased_learning

This model is a fine-tuned version of openai/whisper-medium on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0293
• Wer: 13.7099

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: 3e-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: 1000
• training_steps: 6000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0595	0.4	1000	0.1031	45.0858
0.0357	0.79	2000	0.0648	31.0774
0.0189	1.19	3000	0.0454	23.8119
0.0137	1.58	4000	0.0356	18.2632
0.0086	1.98	5000	0.0308	15.7751
0.0031	2.37	6000	0.0293	13.7099

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.1+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1