whisper-base-tamil

This model is a fine-tuned version of openai/whisper-base on the Common Voice 13 dataset. It achieves the following results on the evaluation set:

• Loss: 0.6483
• Wer Ortho: 72.2910
• Wer: 28.2243

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.003	20.0	500	0.6483	72.2910	28.2243

Framework versions

• Transformers 4.33.0
• Pytorch 2.0.0
• Datasets 2.14.0
• Tokenizers 0.13.3