XLRS-torgo

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: inf
• Wer: 1.6074

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: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
2.554	3.54	400	inf	1.6325
2.3441	7.08	800	inf	1.6406
1.7386	10.62	1200	inf	1.5875
1.0358	14.16	1600	inf	1.6613
0.6366	17.7	2000	inf	1.5348
0.4175	21.24	2400	inf	1.6321
0.3001	24.78	2800	inf	1.5772
0.223	28.32	3200	inf	1.6074

Framework versions

• Transformers 4.23.1
• Pytorch 1.10.0+cu113
• Datasets 1.18.3
• Tokenizers 0.13.1