wav2vec2-large-xls-r-1b-nl-lm

This model is a fine-tuned version of wav2vec2-large-xls-r-1b-nl-lm on the common_voice 8 dataset. It achieves the following results on the test set:

• Loss: 0.1479
• Wer: 0.1156

Note that the above test results come from the original model without LM (language model) which can be found at https://huggingface.co/RuudVelo/wav2vec2-large-xls-r-1b-nl. The results with the LM model can be found on the right side of this model card.

Model description

Model RuudVelo/wav2vec2-large-xls-r-1b-nl which has been improved with a KenLM 5-gram.

Intended uses & limitations

More information needed

Training and evaluation data

Common Voice 8 nl dataset has been used for the model

Training procedure

Training hyperparameters

Parameters can be found in the run.sh file at https://huggingface.co/RuudVelo/wav2vec2-large-xls-r-1b-nl

Framework versions

• Transformers 4.16.0.dev0
• Pytorch 1.10.1+cu102
• Datasets 1.18.3
• Tokenizers 0.11.0