einargizz/whisper_samromur_children

Whisper tiny Icelandic Children

This model is a fine-tuned version of openai/whisper-tiny on the language-and-voice-lab/samromur_children dataset. It achieves the following results on the evaluation set:

• Loss: 0.6313
• Wer: 45.2916

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: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.4343	0.25	250	1.4900	77.9349
0.7722	0.5	500	0.8731	60.2878
0.7181	0.75	750	0.6534	46.5034
0.5733	1.0	1000	0.6313	45.2916

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1
• Datasets 2.10.0
• Tokenizers 0.13.2