whisper-tiny-fo-100h-5k-steps

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

• Loss: 0.4492
• Wer: 35.3131

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: 500
• training_steps: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.7689	0.2320	1000	0.7920	52.4109
0.5534	0.4640	2000	0.5865	44.3024
0.4699	0.6961	3000	0.5051	39.9487
0.4446	0.9281	4000	0.4643	35.9573
0.3597	1.1601	5000	0.4492	35.3131

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1