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

@@ -2,17 +2,26 @@
 
 ### Participants
 
-Yixuan Xu,  Michael Graber
+Yixuan Xu, Roberto Salomone, Michael Graber
 
 ### Previous Action Items
 
 - [ ] Roberto: Confirm huggingface dump for Espresso, Licence for hugging face cc by 4.0 nc (?)
-- [ ] Yixuan: discuss with Imanol how long srg broadcasts should be chunked, if at all
-- [ ] FHNW will prepare spectrograms of Espresso and Regionaljournal and use whisper for music detection if feasible
+- [x] Yixuan: discuss with Imanol how long srg broadcasts should be chunked, if at all
 
 ### Discussion Items
 
 * SG pre-training audio dataset https://www.cs.technik.fhnw.ch/i4ds-datasets -\> Gemeinderat Zürich Audio Corpus
+  * junking would be benificial, \< 2mins 20s
+* Roberto: No update on SSR licence situation
+  * Espresso & Regionaljournal special admission
+* Michael: Transcription model evaluation will be ready this week
+* Yixuan: audio length can be of variable size (junks \< 2 mins 20s if possible), see slack message
+* share code base for pre-processing for processing SPC_R data with Yixuan, most interested in audio speech segmentation with whisper 
+
+### New Action Items
+
+* [ ] Michael : write email with precise license request for the shared Regionaljournal & Espresso data to Roberto
 
 ## Meeting, January 28, 2026