mhaegeman/wav2vec2-large-xls-r-300m-dutch

<!-- 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-large-xls-r-300m-dutch-V2

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

• —eval_loss: 0.4262
• —eval_wer: 0.3052
• —eval_runtime: 8417.9087
• —evalsamplesper_second: 0.678
• —evalstepsper_second: 0.085
• —epoch: 5.33
• —step: 2400

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: 0.0003
• —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_steps: 500
• —num_epochs: 30

Framework versions

• —Transformers 4.11.3
• —Pytorch 1.10.0+cu113
• —Datasets 1.18.3
• —Tokenizers 0.10.3