Update Swiss German Speech Data Meeting Notes authored by Michael Graber's avatar Michael Graber
## Meeting, March 11, 2026
### Participants
Yixuan Xu, Daniel Perruchoud, Michael Graber
### Previous Action Items
* [ ] Roberto: Licence agreement, also partially for Regionaljournal & Espresso broadcasts (needs to be commercially usable and openly shareable)
* [ ] FHNW : translate SFT datasets
### Discussion Points
* SFT datasets in discussion for Swiss German translation (text and audio)
* https://huggingface.co/datasets/deepset/germanquad
https://huggingface.co/datasets/gpt-omni/VoiceAssistant-400K/viewer/default/train?row=27
https://huggingface.co/datasets/lawinstruct/lawinstruct (have to extract german (de))
* FHNW has to identify suitable models (not trained on proprietary data) for translation
* Transcription Evaluation for SRF broadcast transcripts
* FHNW models perform substantially better than current SRF solution
* ![TranscriptionRatingDistributionSRFvsFHNW.png](uploads/f4f0cc084aa9daae243cf90cb83e3485/TranscriptionRatingDistributionSRFvsFHNW.png){width=504 height=360}
* ![TranscriptionModelRatings_FHNW-1vsSRF.png](uploads/1a60f756ecd7ce368cebef5a11aabeb0/TranscriptionModelRatings_FHNW-1vsSRF.png){width=461 height=346}
* ![TranscriptionModelRatings_FHNW-2vsSRF.png](uploads/fad633a86e28d58200bb69dfaa4204e5/TranscriptionModelRatings_FHNW-2vsSRF.png){width=461 height=346}
* \-\> will use FHNW models to generate transcripts, as soon as licencing situation is clarified
### New Action Items
## Meeting, March 4, 2026
### Participants
......
......