abhisheksingh-7/whisper_finetune
016
<!-- 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. -->
Whisper Tiny En - Abhishek Singh
This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 13.0 dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.5896
- eval_wil: 42.8626
- eval_runtime: 1949.885
- evalsamplesper_second: 5.129
- evalstepsper_second: 0.641
- epoch: 0.05
- step: 24000
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: 16
- evalbatchsize: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lrschedulertype: linear
- lrschedulerwarmup_steps: 500
- training_steps: 500000
- mixedprecisiontraining: Native AMP
Framework versions
- Transformers 4.29.0.dev0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3