whisper_large_v3_turbo_noise_redux_v3

This model is a fine-tuned version of openai/whisper-large-v3-turbo on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.3321
• eval_runtime: 52.839
• eval_samples_per_second: 10.901
• eval_steps_per_second: 10.901
• epoch: 2.5
• step: 60

Model description

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.002
• train_batch_size: 6
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 24
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.39.3
• Pytorch 2.4.1+cu124
• Datasets 2.18.0
• Tokenizers 0.15.2