whisper-tiny-tr-0904

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

• epoch: 1.0
• eval_loss: 0.5816
• eval_runtime: 2424.1201
• eval_samples_per_second: 3.564
• eval_steps_per_second: 0.014
• eval_wer: 57.8745
• step: 415

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: 64
• eval_batch_size: 256
• seed: 42
• optimizer: Use adamw_8bit 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: 100
• num_epochs: 3.0
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.51.1
• Pytorch 2.5.1+cu121
• Datasets 3.5.0
• Tokenizers 0.21.0