MCV_Fleurs_Combined_Irish_ASR_with_Aug2

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

• Loss: 0.3801
• Wer: 23.6235

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: 0.0005
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• 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: 25000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.5290	5.7339	2500	0.4228	39.4243
0.1859	11.4679	5000	0.4204	35.9643
0.0914	17.2018	7500	0.4188	35.1018
0.0749	22.9358	10000	0.4176	32.0580
0.0537	28.6697	12500	0.4198	31.0751
0.0206	34.4037	15000	0.4003	28.1466
0.0205	40.1376	17500	0.3931	27.6953
0.0150	45.8716	20000	0.3856	25.3285
0.0058	51.6055	22500	0.3831	23.8943
0.0040	57.3394	25000	0.3801	23.6235

Framework versions

• Transformers 5.6.0.dev0
• Pytorch 2.9.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.2