whisper-small-hyper-tuned

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

• eval_loss: 0.2633
• eval_runtime: 1409.8172
• eval_samples_per_second: 8.111
• eval_steps_per_second: 1.014
• epoch: 0.1650
• step: 500

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: 2.5e-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: 300
• training_steps: 1000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.45.1
• Pytorch 2.1.0+cu118
• Datasets 3.0.1
• Tokenizers 0.20.0