Achitha/10th_science_ta_to_eng
05
<!-- 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. -->
10thsciencetatoeng
This model is a fine-tuned version of openai/whisper-base on the 10thsciencetamiltoenglish dataset. It achieves the following results on the evaluation set:
- eval_loss: 4.2536
- eval_wer: 133.3041
- eval_runtime: 194.5706
- evalsamplesper_second: 1.994
- evalstepsper_second: 0.128
- epoch: 13.0
- step: 5000
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
- trainbatchsize: 32
- evalbatchsize: 16
- seed: 42
- gradientaccumulationsteps: 2
- totaltrainbatch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lrschedulertype: linear
- lrschedulerwarmup_steps: 500
- training_steps: 5000
- mixedprecisiontraining: Native AMP
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.10.2.dev0
- Tokenizers 0.13.2