whisper-medium-1.3

This model is a fine-tuned version of hts98/whisper-medium-1113 on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.2185
• eval_wer: 99.8842
• eval_runtime: 175.2878
• eval_samples_per_second: 4.883
• eval_steps_per_second: 0.411
• epoch: 2.11
• step: 600

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: 12
• eval_batch_size: 12
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 200
• training_steps: 1400
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.27.0.dev0
• Pytorch 1.12.1+cu113
• Datasets 2.7.0
• Tokenizers 0.12.1