Skip to main content

sbx-swe-speech2text-transformers-kb_whisper_mp3

Analysis citation Information

Språkbanken Text. sbx-swe-speech2text-transformers-kb_whisper_mp3 [Analysis]. Språkbanken Text. https://doi.org/10.23695/6nry-qr23
BibTeX Additional ways to cite the dataset.
Transcribing audio file (mp3) to text by transformers and KB-Whisper for Swedish

Example

This importer is used with Sparv. Check out Sparv's quick start guide to get started!

To use this importer, run Sparv with the argument 'sbx_whisper_import:parse_mp3':

sparv run sbx_whisper_import:parse_mp3

You also need to install the following plugin: sbx_whisper_import.

For general information on how to install plugins, see here.

For more info on how to use Sparv, check out the Sparv documentation.

Other references

  • Swedish Whispers; Leveraging a Massive Speech Corpus for Swedish Speech Recognition - Vesterbacka et al - 2025 - Interspeech 2025, p758-762 - doi: 10.21437/Interspeech.2025-2646

Type

  • Utility

Dependencies

External tools

transformers
Apache-2.0 license

Models

KBLab/kb-whisper-tiny
The National Library of Sweden releases a new suite of Whisper models trained on over 50,000 hours of Swedish speech.
Apache-2.0 license

Keyword

  • whisper
  • transformers
  • huggingface

Created

2025-09-04

Contact

sb-info@svenska.gu.se