whisper-large-v3-ft-btb-cv-cvad-ca-cy-2503

This model is a fine-tuned version of openai/whisper-large-v3 on the DewiBrynJones/banc-trawsgrifiadau-bangor train main, DewiBrynJones/commonvoice_18_0_cy train+dev+other_with_excluded main, cymen-arfor/lleisiau-arfor train+dev main, techiaith/commonvoice_vad_cy train main dataset. It achieves the following results on the evaluation set:

• Loss: 0.3739
• Wer: 0.2915

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
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Use 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: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.5304	0.3240	1000	0.5236	0.3786
0.4409	0.6480	2000	0.4458	0.3563
0.3914	0.9720	3000	0.4035	0.3090
0.296	1.2958	4000	0.3868	0.2977
0.274	1.6198	5000	0.3739	0.2915

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0