Edit model card
YAML Metadata Error: "language[0]" must only contain lowercase characters
YAML Metadata Error: "language[0]" with value "nb-NO" is not valid. It must be an ISO 639-1, 639-2 or 639-3 code (two/three letters), or a special value like "code", "multilingual". If you want to use BCP-47 identifiers, you can specify them in language_bcp47.

Norwegian Wav2Vec2 Model - 300M - VoxRex - Bokmål

This model is finetuned on top of feature extractor VoxRex-model from the National Library of Sweden. The finetuned model achieves the following results on the test set with a 5-gram KenLM. The numbers in parentheses are the results without the language model:

  • WER: 0.0703 (0.0979)
  • CER: 0.0269 (0.0311)

Model description

This is one of several Wav2Vec-models our team created during the 🤗 hosted Robust Speech Event. This is the complete list of our models and their final scores:

Model Final WER
NbAiLab/nb-wav2vec2-1b-bokmaal 6.33
NbAiLab/nb-wav2vec2-300m-bokmaal (this model) 7.03
NbAiLab/nb-wav2vec2-300m-nynorsk 12.22


In parallel with the event, the team also converted the Norwegian Parliamentary Speech Corpus (NPSC) to the NbAiLab/NPSC in 🤗 Dataset format and used that as the main source for training.


We have released all the code developed during the event so that the Norwegian NLP community can build upon it when developing even better Norwegian ASR models. The finetuning of these models is not very computationally demanding. After following the instructions here, you should be able to train your own automatic speech recognition system in less than a day with an average GPU.


The following people contributed to building this model: Rolv-Arild Braaten, Per Egil Kummervold, Andre Kåsen, Javier de la Rosa, Per Erik Solberg, and Freddy Wetjen.

Training procedure

To reproduce these results, we strongly recommend that you follow the instructions from 🤗 to train a simple Swedish model.

When you have verified that you are able to do this, create a fresh new repo. You can then start by copying the files run.sh and run_speech_recognition_ctc.py from our repo. Running these will create all the other necessary files, and should let you reproduce our results. With some tweaks to the hyperparameters, you might even be able to build an even better ASR. Good luck!

Language Model

As the scores indicate, adding even a simple 5-gram language will improve the results. 🤗 has provided another very nice blog explaining how to add a 5-gram language model to improve the ASR model. You can build this from your own corpus, for instance by extracting some suitable text from the Norwegian Colossal Corpus. You can also skip some of the steps in the guide, and copy the 5-gram model from this repo.


The final model was run using these parameters:

--do_train --do_eval 

Using these settings, the training might take 3-4 days on an average GPU. You can, however, get a decent model and faster results by tweaking these parameters.

Parameter Comment
per_device_train_batch_size Adjust this to the maximum of available memory. 16 or 24 might be good settings depending on your system
gradient_accumulation_steps Can be adjusted even further up to increase batch size and speed up training without running into memory issues
learning_rate Can be increased, maybe as high as 1e-4. Speeds up training but might add instability
epochs Can be decreased significantly. This is a huge dataset and you might get a decent result already after a couple of epochs
Downloads last month
Hosted inference API
or or
This model can be loaded on the Inference API on-demand.

Dataset used to train NbAiLab/nb-wav2vec2-300m-bokmaal

Evaluation results