xls-r-1b-bem-msv

This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on the BEMBASPEECH - BEM dataset. It achieves the following results on the evaluation set:

• Loss: 0.1348
• Wer: 0.6038

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-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 5.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
2.4467	1.0406	500	0.2477	0.8371
0.4021	2.0812	1000	0.1869	0.7790
0.3192	3.1217	1500	0.1469	0.6581
0.2252	4.1623	2000	0.1348	0.6038

Framework versions

• Transformers 4.43.0
• Pytorch 2.3.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1