Mukund017/whisper-small-kannada

Whisper Small Ka -Tripti

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: 0.2298
• Wer: 42.9768

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: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0238	6.0606	1000	0.1512	45.2296
0.0021	12.1212	2000	0.2023	43.6566
0.0001	18.1818	3000	0.2234	43.0085
0.0001	24.2424	4000	0.2298	42.9768

Framework versions

• Transformers 4.40.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1