rdomanski/whisper-small-pl

openai/whisper-small Pl - RDO

This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4041
• Wer: 29.2371

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: 8
• 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: 50
• training_steps: 400
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.5396	0.32	100	0.5780	38.4080
0.3311	0.64	200	0.4404	31.8076
0.279	0.96	300	0.4180	31.2604
0.144	1.29	400	0.4041	29.2371

Framework versions

• Transformers 4.39.0.dev0
• Pytorch 2.2.1+cu118
• Datasets 2.17.1
• Tokenizers 0.15.2