whisper-small-ee

<!-- 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. -->

UG Speech Data ASR - Ewe nornmaliser

This model is a fine-tuned version of openai/whisper-small on the ugspeechdata-ewe dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.4720
• eval_wer_ortho: 45.4249
• eval_wer: 37.4757
• eval_cer: 12.9706
• eval_runtime: 1781.9648
• eval_samples_per_second: 2.159
• eval_steps_per_second: 0.135
• epoch: 2.8708
• step: 2400

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 4.50.0
• Pytorch 2.6.0+cu124
• Tokenizers 0.21.1