Tobius/youtube-whisper-base-en
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. -->
Whisper base ganda
This model is a fine-tuned version of openai/whisper-base on the Youtube data dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.4484
- eval_wer: 8.6957
- eval_runtime: 3.9989
- evalsamplesper_second: 2.001
- evalstepsper_second: 2.001
- epoch: 357.1429
- step: 2500
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: 4
- evalbatchsize: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lrschedulertype: linear
- lrschedulerwarmup_steps: 500
- training_steps: 15000
- mixedprecisiontraining: Native AMP
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1