whisper-small-dv

This model is a fine-tuned version of openai/whisper-tiny on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:

• Loss: 0.7484
• Wer Ortho: 0.3325
• Wer: 0.3353

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: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.0004	62.5	500	0.6841	0.3399	0.3424
0.0002	125.0	1000	0.7484	0.3325	0.3353

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu118
• Datasets 2.19.1
• Tokenizers 0.19.1