whisper-medium-jiaozhu

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

• eval_loss: 0.0090
• eval_wer: 11.9565
• eval_runtime: 110.4355
• eval_samples_per_second: 0.833
• eval_steps_per_second: 0.109
• epoch: 2.3913
• step: 55

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: 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: 50
• training_steps: 500
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu118
• Datasets 2.20.0
• Tokenizers 0.19.1