arun100/whisper-small-is_is

Whisper Small Icelandic

This model is a fine-tuned version of openai/whisper-small on the google/fleurs is_is dataset. It achieves the following results on the evaluation set:

• Loss: 1.6747
• Wer: 66.5053

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: 64
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 3000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0002	499.0	1000	1.6747	66.5053
0.0001	999.0	2000	1.7714	67.6670
0.0	1499.0	3000	1.8178	68.6350

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.1+cu117
• Datasets 2.8.1.dev0
• Tokenizers 0.13.2