bayartsogt/whisper-medium-mn-5

whisper-medium-mn-4

This model is a fine-tuned version of openai/whisper-medium on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3396
• Wer: 24.7268
• Cer: 8.6712

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: 32
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 12000
• mixed_precision_training: Native AMP

Training results

{'eval_loss': 0.3396347761154175, 'eval_wer': 24.7268953462967, 'eval_cer': 8.671234994074913, 'eval_runtime': 2202.1539, 'eval_samples_per_second': 0.856, 'eval_steps_per_second': 0.027, 'epoch': 7
.3}                                                                                                                                                                                                   

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu117
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2