wav2vec2-xls-r-300m-bangla-command-synthetic

This model is a fine-tuned version of sshasnain/wav2vec2-xls-r-300m-bangla-command on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.0254
• eval_wer: 0.4311
• eval_runtime: 2.5036
• eval_samples_per_second: 76.689
• eval_steps_per_second: 9.586
• epoch: 35.71
• step: 1000

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: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• num_epochs: 100
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.16.2
• Pytorch 1.10.0+cu111
• Datasets 1.18.3
• Tokenizers 0.11.0