S-Sethisak/whisper-kh-en

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