whisper-tiny-no-is-5k-steps

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

• Loss: 0.7830
• Wer: 51.6035

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
1.2696	0.1778	1000	1.3551	69.4512
0.9101	0.3556	2000	0.9833	60.0096
0.7626	0.5333	3000	0.8596	54.7590
0.7316	0.7111	4000	0.8014	52.3165
0.7269	0.8889	5000	0.7830	51.6035

Framework versions

• Transformers 4.42.3
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1