bhattasp/whisper-finetuned-bial2

This model is a fine-tuned version of openai/whisper-tiny on the bial2 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3088
• Wer: 29.3953

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: 2000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1482	4.3290	1000	0.3253	31.3301
0.0563	8.6580	2000	0.3088	29.3953

Framework versions

• Transformers 4.43.3
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1