whisper-small-kn

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

• eval_loss: 0.3241
• eval_wer: 65.9127
• eval_runtime: 977.4817
• eval_samples_per_second: 1.023
• eval_steps_per_second: 0.064
• epoch: 3.2
• step: 4000

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: 4
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• 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: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 8000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.52.0
• Pytorch 2.8.0+cu128
• Datasets 4.1.1
• Tokenizers 0.21.2