safecantonese/whisper-small-yue
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-small-yue-full
This model is a fine-tuned version of wcyat/whisper-small-yue on the None dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.2532
- eval_cer: 11.9313
- eval_runtime: 1178.2632
- evalsamplesper_second: 2.191
- evalstepsper_second: 0.137
- 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: 16
- evalbatchsize: 16
- seed: 42
- gradientaccumulationsteps: 2
- totaltrainbatch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lrschedulertype: linear
- lrschedulerwarmup_steps: 500
- training_steps: 2000
- mixedprecisiontraining: Native AMP
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1