audiox_fleurs_no_lang_id_fleurs_49398_trial

This model is a fine-tuned version of jiviai/audioX-north-v1 on the fleurs dataset. It achieves the following results on the evaluation set:

• Loss: 0.0984
• Global Wer: 78.3728

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 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
0.1728	0.0945	50	0.1519	62.3268
0.113	0.1890	100	0.1177	16.0165
0.0771	0.2836	150	0.0968	33.8803
0.0909	0.3781	200	0.0922	62.9164
0.0892	0.4726	250	0.0982	62.7788
0.0884	0.5671	300	0.0957	77.2035
0.0825	0.6616	350	0.0930	54.8786
0.0902	0.7561	400	0.0962	70.2172
0.072	0.8507	450	0.0972	88.7983
0.0894	0.9452	500	0.0984	78.3728

Framework versions

• Transformers 4.50.0
• Pytorch 2.9.0+cu126
• Datasets 3.6.0
• Tokenizers 0.21.4