rohitp1/dgx1_whisper_base_mozilla_noisy_teacher_distil_epochs_50_batch_16

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

dgx1whisperbasemozillanoisyteacherdistilepochs50batch16

This model is a fine-tuned version of rohitp1/dgx1_whisper_base_finetune_teacher_babble_noise_mozilla_100_epochs_batch_16 on the None dataset. It achieves the following results on the evaluation set:

• —Loss: 1.0845
• —Wer: 33.7337

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: 5e-05
• —trainbatchsize: 16
• —evalbatchsize: 1
• —seed: 42
• —gradientaccumulationsteps: 256
• —totaltrainbatch_size: 4096
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: cosinewithrestarts
• —lrschedulerwarmup_ratio: 0.2
• —num_epochs: 50
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 4.25.1
• —Pytorch 1.12.1
• —Datasets 2.8.0
• —Tokenizers 0.13.2