wh_small_fleurs_fleurs_52027_trial

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: 0.2929
• Global Wer: 33.3792

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: 5e-06
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Use adamw_torch_fused 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: 500

Training results

Training Loss	Epoch	Step	Validation Loss	Global Wer
0.7979	0.0945	50	0.6360	51.0858
0.5752	0.1890	100	0.5197	44.1093
0.4703	0.2836	150	0.4626	41.2401
0.4566	0.3781	200	0.4261	38.7246
0.4171	0.4726	250	0.3962	36.1698
0.3705	0.5671	300	0.3733	38.1940
0.3434	0.6616	350	0.3459	34.9907
0.3215	0.7561	400	0.3286	33.8410
0.3001	0.8507	450	0.3094	33.5561
0.2756	0.9452	500	0.2929	33.3792

Framework versions

• Transformers 5.0.0.dev0
• Pytorch 2.9.0+cu126
• Datasets 3.6.0
• Tokenizers 0.22.2