anuragshas/wav2vec2-xlsr-53-rm-vallader-with-lm

<!-- 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. -->

wav2vec2-xlsr-53-rm-vallader-with-lm

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

• —Loss: 0.4552
• —Wer: 0.3206

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
• —trainbatchsize: 16
• —evalbatchsize: 8
• —seed: 42
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 32
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_ratio: 0.112
• —num_epochs: 30

Training results

Framework versions

• —Transformers 4.15.0
• —Pytorch 1.10.0+cu111
• —Datasets 1.18.1
• —Tokenizers 0.10.3