PThi35/whisper_large_v3_phase3
01
<!-- 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. -->
whisperlargev3_phase3
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.7053
- evalmodelpreparation_time: 0.0154
- eval_cer: 16.8825
- eval_wer: 28.2705
- eval_runtime: 2657.6234
- evalsamplesper_second: 1.318
- evalstepsper_second: 0.165
- step: 0
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: 8
- evalbatchsize: 8
- seed: 42
- gradientaccumulationsteps: 2
- totaltrainbatch_size: 16
- optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
- lrschedulertype: linear
- lrschedulerwarmup_steps: 1000
- num_epochs: 20
- mixedprecisiontraining: Native AMP
Framework versions
- Transformers 4.55.4
- Pytorch 2.8.0+cu126
- Datasets 4.1.1
- Tokenizers 0.21.4