rohitp1/distil_noisy_teacher_clean_student_data_libri
06
<!-- 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. -->
distilnoisyteachercleanstudentdatalibri
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset. It achieves the following results on the evaluation set:
- Loss: 153.4607
- Wer: 0.8504
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: 0.0005
- trainbatchsize: 8
- evalbatchsize: 1
- seed: 42
- gradientaccumulationsteps: 256
- totaltrainbatch_size: 2048
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lrschedulertype: cosine
- lrschedulerwarmup_ratio: 0.2
- num_epochs: 100
- mixedprecisiontraining: Native AMP
Training results
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1
- Datasets 2.6.1
- Tokenizers 0.13.1