Pageee/FT-English-1ha
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-Small En-10m
This model is a fine-tuned version of openai/whisper-small on the librispeech dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.1637
- eval_wer: 4.1501
- eval_runtime: 545.5827
- evalsamplesper_second: 4.48
- evalstepsper_second: 0.561
- epoch: 76.9231
- step: 1500
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: 5e-07
- trainbatchsize: 8
- evalbatchsize: 8
- seed: 42
- gradientaccumulationsteps: 2
- totaltrainbatch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lrschedulertype: linear
- lrschedulerwarmup_steps: 300
- training_steps: 2000
- mixedprecisiontraining: Native AMP
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1