simran14/mr-val-b

simrank14 Whisper small valB

This model is a fine-tuned version of simran14/mr-val-a on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.0413
• Wer: 3.0369

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: 100
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.105	0.7337	1000	0.0767	6.2825
0.0532	1.4674	2000	0.0413	3.0369

Framework versions

• Transformers 4.45.0.dev0
• Pytorch 2.3.1+cu121
• Datasets 2.21.1.dev0
• Tokenizers 0.19.1