adrianSauer/wav2vec2-cer-extension

<!-- 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. -->

Common Voice 16

This model is a fine-tuned version of glob-asr/wav2vec2-large-xls-r-300m-guarani-small on the Common Voice 16 dataset. It achieves the following results on the evaluation set:

• —Loss: 0.2425
• —Cer: 5.9170

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: 5e-05
• —trainbatchsize: 8
• —evalbatchsize: 16
• —seed: 42
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 16
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: constantwithwarmup
• —lrschedulerwarmup_steps: 3000
• —training_steps: 3000
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 4.44.1
• —Pytorch 2.3.1+cu121
• —Datasets 2.21.0
• —Tokenizers 0.19.1