Whisper-Small-kh
This model is a fine-tuned version of openai/whisper-small on the Fleur dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.4535
- eval_wer_ortho: 99.1998
- eval_wer: 49.3369
- eval_runtime: 465.0049
- eval_samples_per_second: 1.544
- eval_steps_per_second: 0.097
- epoch: 25.4237
- step: 3000
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
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 4000
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.48.0
- Pytorch 2.6.0+cu124
- Datasets 2.14.7
- Tokenizers 0.21.4
- Downloads last month
- 3
Model tree for S-Sethisak/whisper-kh-en
Base model
openai/whisper-small