Swiss-German-Speech-Data---Meeting-Notes.md

+## Meeting May 20, 2026
+
+### Participants
+
+Yixuan Xu, Daniel Perruchoud, Roberto Salomone, Fabian Jeitziner, Michael Graber
+
+### Previous Action Items
+
+* [x] Propose next steps for SFT data
+* [ ] Roberto: Licence agreement, also partially for Regionaljournal & Espresso broadcasts (needs to be commercially usable and openly shareable)
+
+### Discussion Items
+
+* Performance of current Apertus checkpoints seems better than any other open model
+* SFT training paradigms / datasets
+  * https://huggingface.co/datasets/gpt-omni/VoiceAssistant-400K 
+  * https://huggingface.co/datasets/Harland/AudioMCQ-StrongAC-GeminiCoT
+  * https://huggingface.co/datasets/AIDC-AI/Marco_Longspeech
+* 
+
+## Meeting May 13, 2026
+
+### Participants
+
+Yixuan Xu, Daniel Perruchoud, Roberto Salomone, Fabian Jeitziner, Michael Graber
+
+NO NOTES
+
 ## Meeting April 29, 2026
 
 ### Participants
@@ -18,7 +46,7 @@ Yixuan Xu, Daniel Perruchoud, Roberto Salomone, Michael Graber
   * More data would help even more!
   * However, we should find more human labelled transcripts (only working with pseudo-labelled data is considered problematic)
     * Maybe archive data would be useful
-* Roberto: license draft has been iterate on, next board meeting is in June is 
+* Roberto: license draft has been iterate on, next board meeting is in June is
 
 ### New Action Points