wh_small_fl_fleurs_47695_trial

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

• Loss: 0.4378
• Global Wer: 50.1636

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
1.5906	0.0122	50	1.2327	78.5714
0.9574	0.0244	100	0.9683	67.6118
0.8153	0.0365	150	0.8526	66.2486
0.7532	0.0487	200	0.7511	58.2879
0.6401	0.0609	250	0.6685	55.5071
0.5666	0.0731	300	0.5905	59.3239
0.5114	0.0853	350	0.5146	52.3446
0.4350	0.0974	400	0.4670	54.9073
0.4325	0.1096	450	0.4477	59.6510
0.4297	0.1218	500	0.4378	50.1636

Framework versions

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