Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,23 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
## Citation
|
| 6 |
+
|
| 7 |
+
```bibtex
|
| 8 |
+
@inproceedings{de-la-rosa-etal-2023-boosting,
|
| 9 |
+
title = "Boosting {N}orwegian Automatic Speech Recognition",
|
| 10 |
+
author = "De La Rosa, Javier and
|
| 11 |
+
Braaten, Rolv-Arild and
|
| 12 |
+
Kummervold, Per and
|
| 13 |
+
Wetjen, Freddy",
|
| 14 |
+
booktitle = "Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)",
|
| 15 |
+
month = may,
|
| 16 |
+
year = "2023",
|
| 17 |
+
address = "T{\'o}rshavn, Faroe Islands",
|
| 18 |
+
publisher = "University of Tartu Library",
|
| 19 |
+
url = "https://aclanthology.org/2023.nodalida-1.55",
|
| 20 |
+
pages = "555--564",
|
| 21 |
+
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 sizes and pre-training approaches on multiple Norwegian speech datasets. Additionally, we measure the performance of these models against previous state-of-the-art ASR models, as well as on out-of-domain datasets. We improve the state of the art on the Norwegian Parliamentary Speech Corpus (NPSC) from a word error rate (WER) of 17.10{\%} to 7.60{\%}, with models achieving 5.81{\%} for Bokm{\aa}l and 11.54{\%} for Nynorsk. We also discuss the challenges and potential solutions for further improving ASR models for Norwegian.",
|
| 22 |
+
}
|
| 23 |
+
```
|