auditi41/Wav2Vec2LargeXlsr53-Bangla

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

Wav2Vec2LargeXlsr53-Bangla

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the commonvoice11_0 dataset. It achieves the following results on the evaluation set:

• —Loss: 0.4997
• —Wer: 0.4970

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: 0.0004
• —trainbatchsize: 24
• —evalbatchsize: 8
• —seed: 42
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 48
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 500
• —num_epochs: 20

Training results

Framework versions

• —Transformers 4.24.0
• —Pytorch 2.0.0+cu118
• —Datasets 2.11.0
• —Tokenizers 0.13.3