This is a large wav2vec2 model (1B parameters) fine-tuned by the Norwegian AI Lab for automatic speech recognition on Nynorsk Norwegian. It was trained on the NPSC dataset and achieves strong performance on Norwegian speech. The model is available through the Hugging Face Transformers library.
Nb Wav2vec2 1b Nynorsk is a Voice, TTS & speech product. It focuses on transcribing spoken Nynorsk Norwegian audio into text. Nb Wav2vec2 1b Nynorsk is an open-source project aimed at developers. The project is open source (Apache-2.0). It runs on the web and API.
NbAiLab builds and maintains Nb Wav2vec2 1b Nynorsk, and the product first shipped in 2018. The project is developed in the open on GitHub with 163k stars and 762 commits in the last 90 days. Among its 3 catalogued features are Automatic Speech Recognition, Nynorsk Support, and Norwegian ASR.
Latest indexed changes and source events
NbAiLab/nb-wav2vec2-1b-nynorsk verified by the PulseGate indexer
Other apps tracked under the same category.
