wav2vec2-E50

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 4.4959
• Cer: 89.8179

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• 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: linear
• lr_scheduler_warmup_steps: 50
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
28.4775	0.2581	200	5.5054	100.0
4.6583	0.5161	400	5.0085	91.3690
4.4404	0.7742	600	5.2442	92.5264
4.3414	1.0323	800	4.9330	90.7109
4.3064	1.2903	1000	4.8601	90.7814
4.2331	1.5484	1200	4.9136	92.1034
4.2258	1.8065	1400	5.0350	90.3702
4.1731	2.0645	1600	5.0754	90.3995
4.1586	2.3226	1800	4.7405	89.2773
4.1386	2.5806	2000	4.6875	90.8578
4.1294	2.8387	2200	4.4959	89.8179

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0