whisper-small-dv

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

whisper-small-dv

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

• Loss: 0.2256
• Wer Ortho: 36.7208
• Wer: 12.2160

Model description

This is the small variant of Whisper model.

Intended uses & limitations

Fine Tuned on the tamil split of Fleurs hence Made for Tamil ASR

Training and evaluation data

Not so Great, trained on Google Colab

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.48.0
• Pytorch 2.8.0+cu126
• Datasets 3.6.0
• Tokenizers 0.21.4