wav2vec2-xls-r-ewe-20-hours

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: 0.7162
• Wer: 0.3681
• Cer: 0.1051

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: 0.0003
• train_batch_size: 32
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Use OptimizerNames.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_ratio: 0.1
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
8.2538	8.4034	500	0.5225	0.4745	0.1342
0.8974	16.8067	1000	0.4220	0.3655	0.1072
0.5528	25.2101	1500	0.5054	0.3678	0.1054
0.3461	33.6134	2000	0.6326	0.3765	0.1080
0.2328	42.0168	2500	0.7162	0.3681	0.1051

Framework versions

• Transformers 4.46.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.20.3