wav2vec2-xls-r-300m-mt-50

This model was fine-tuned on a combined dataset.

Sample usage is included with Run_ASR_Pipeline.py

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0003
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• 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

Framework versions

• Transformers 4.16.2
• Pytorch 1.10.2
• Datasets 1.18.4
• Tokenizers 0.10.3

License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. Permissions beyond the scope of this license may be available at https://mlrs.research.um.edu.mt/.