KB-Whisper: Swedish speech recognition models

KB-Whisper: Swedish speech recognition models

Open Model

By National Library of Sweden

Whisper speech-to-text models for Swedish from KBLab at the National Library of Sweden, trained on more than 50,000 hours of Swedish speech; the library reports a 47% lower average word error rate than OpenAI's whisper-large-v3 in its evaluations. Apache 2.0.

  • Use cases, geography and tags
  • Organizations that created, adopted or are mentioned
  • Ecosystem position
  • Link to the original asset
  • Comments and reactions