whisper-small-en2hi

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

• Loss: 0.0595
• Wer: 25.2083

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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• 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
0.016	0.2	1000	0.0664	19.5629
0.0228	0.4	2000	0.0646	24.0922
0.0347	0.6	3000	0.0655	31.0635
0.048	0.8	4000	0.0621	36.7658
0.0264	1.0	5000	0.0595	25.2083

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.5.0
• Tokenizers 0.21.0