wav2vec2_murad

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the cvbn dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.2006
• eval_wer: 0.2084
• eval_runtime: 556.4634
• eval_samples_per_second: 8.985
• eval_steps_per_second: 0.562
• epoch: 12.32
• step: 28800

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: 7.5e-05
• train_batch_size: 16
• eval_batch_size: 16
• 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: 30
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.21.1
• Pytorch 1.11.0+cu102
• Datasets 2.4.0
• Tokenizers 0.12.1