enakilci/whisper-large-v3-fi-800steps-8batch-2grad_steps-5e-05lr-poly

Whisper Large v3 Fine-Tuned Finnish

This model is a fine-tuned version of openai/whisper-large-v3 on the Common Voice 13.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.249
• Wer: 23.366

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: polynomial
• lr_scheduler_kwargs = { 'lr_end': 1e-05 }
• training_steps: 800
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.6193	0.21	50	0.2905	29.1920
0.3266	0.84	200	0.3132	28.333
0.1382	1.68	400	0.3139	27.591
0.0551	2.53	600	0.2957	25.75
0.0158	3.37	800	0.2490	23.366

Framework versions

• Transformers 4.37.0.dev0
• Pytorch 2.0.1
• Datasets 2.16.1
• Tokenizers 0.15.0