aware-ai/wav2vec2-xls-r-1b-german

<!-- 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-xls-r-1b-german

This model is a fine-tuned version of wav2vec2-xls-r-1b-german on the MOZILLA-FOUNDATION/COMMONVOICE10_0 - DE dataset. It achieves the following results on the evaluation set:

• —Loss: 0.3513
• —Wer: 0.2931

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: 3e-07
• —trainbatchsize: 48
• —evalbatchsize: 48
• —seed: 42
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 96
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —num_epochs: 2.0
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 4.21.3
• —Pytorch 1.12.1
• —Datasets 2.4.0
• —Tokenizers 0.12.1