wh_small_fl_no_langid_fleurs_47716_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: 0.2928
• Global Wer: 39.1667

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
0.6858	0.0945	50	0.5392	55.3503
0.4892	0.1890	100	0.4350	47.4993
0.3921	0.2836	150	0.3903	44.8364
0.3917	0.3781	200	0.3638	42.1735
0.3594	0.4726	250	0.3443	40.4245
0.3264	0.5671	300	0.3306	40.8863
0.3102	0.6616	350	0.3162	39.0095
0.3000	0.7561	400	0.3102	38.0662
0.2897	0.8507	450	0.3021	38.0466
0.2747	0.9452	500	0.2928	39.1667

Framework versions

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