nb-wav2vec2-bokmaal

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:

Dataset

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.

Code

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.

Team

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.

Parameters

The final model was run using these parameters:

--dataset_name="NbAiLab/NPSC"
--model_name_or_path="facebook/wav2vec2-xls-r-1b"
--dataset_config_name="16K_mp3_bokmaal"
--output_dir="./"
--overwrite_output_dir
--num_train_epochs="40"
--per_device_train_batch_size="12"
--per_device_eval_batch_size="12"
--gradient_accumulation_steps="2"
--learning_rate="2e-5"
--warmup_steps="2000"
--length_column_name="input_length"
--evaluation_strategy="steps"
--text_column_name="text"
--save_steps="500"
--eval_steps="500"
--logging_steps="100"
--layerdrop="0.041"
--attention_dropout="0.094"
--activation_dropout="0.055"
--hidden_dropout="0.047"
--save_total_limit="3"
--freeze_feature_encoder
--feat_proj_dropout="0.04"
--mask_time_prob="0.082"
--mask_time_length="10"
--mask_feature_prob="0.25"
--mask_feature_length="64"
--gradient_checkpointing
--min_duration_in_seconds="0.5"
--max_duration_in_seconds="30.0"
	--ctc_zero_infinity=True
--use_auth_token
--seed="42"
--fp16
--group_by_length
--do_train --do_eval
--push_to_hub
--preprocessing_num_workers="16"

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.

## Citation

@inproceedings{de-la-rosa-etal-2023-boosting,
    title = "Boosting {N}orwegian Automatic Speech Recognition",
    author = "De La Rosa, Javier  and
      Braaten, Rolv-Arild  and
      Kummervold, Per  and
      Wetjen, Freddy",
    booktitle = "Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)",
    month = may,
    year = "2023",
    address = "T{\'o}rshavn, Faroe Islands",
    publisher = "University of Tartu Library",
    url = "https://aclanthology.org/2023.nodalida-1.55",
    pages = "555--564",
    abstract = "In this paper, we present several baselines for automatic speech recognition (ASR) models for the two official written languages in Norway: Bokm{\aa}l and Nynorsk. We compare the performance of models of varying siz