Elie/whisper-small-fleurs-ln_cd

Whisper Small Lingala

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

• Loss: 0.5608
• Wer: 19.8362

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: 8
• 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: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 3000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0939	4.7619	1000	0.4101	20.1182
0.0034	9.5238	2000	0.4968	19.7772
0.0013	14.2857	3000	0.5139	19.3226

Framework versions

• Transformers 4.48.2
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0