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

@@ -6,18 +6,18 @@ Yixuan Xu, Michael Graber
 
 ### Previous Action Items
 
-* [ ] Roberto: Confirm huggingface dump for Espresso, Regionaljournal Licence for hugging face cc by 4.0 nc (?)
+* [ ] Roberto: Licence agreement, also partially for Regionaljournal & Espresso broadcasts (needs to be commercially usable and openly shareable) 
 
 ### Discussion Points
 
-* SRF data sample shared by Fiona works for Yixuan
-* Yixuan shares tokenization pipeline:
+* SRF data sample shared by Fiona structurally works for Yixuan, licence remains to be clarified by SRF
+* Yixuan - tokenization pipeline : https://github.com/swiss-ai/benchmark-audio-tokenizer/blob/batch_tok/audio_tokenization/README.md
 * Michael: Transcription evaluation on its way, first results indicate FHNW transcription models to be substantially superior to models used by SRF
-* FHNW : Industry Fine-Tuning case is ready and could be discussed
+* FHNW (via Daniel): Industry Fine-Tuning case is in pipeline with company and could be discussed with Apertus team (Imanol?)
 
 ### New Action Items
 
-* @FHNW : translate SFT dataset shared by Yixuan
+* FHNW : translate SFT dataset shared by Yixuan
 
 ## Meeting, February 25, 2026