Nonstudio_Studio_Whisper_Medium

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: 0.0313
• Wer: 14.9042

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: 1000
• training_steps: 6000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0611	0.38	1000	0.0875	42.0254
0.0348	0.77	2000	0.0556	29.6840
0.0195	1.15	3000	0.0459	23.8368
0.0133	1.53	4000	0.0373	19.1092
0.0138	1.92	5000	0.0318	16.5962
0.004	2.3	6000	0.0313	14.9042

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.1+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1