Update Swiss German Speech Data Meeting Notes authored by Michael Graber's avatar Michael Graber
...@@ -16,12 +16,12 @@ Yixuan Xu, Michael Graber ...@@ -16,12 +16,12 @@ Yixuan Xu, Michael Graber
* license * license
* use qwen: timbre generation model ? * use qwen: timbre generation model ?
* Yixuan shares demo on slack for SG * Yixuan shares demo on slack for SG
* Currently the performance on audio is not very good yet * Currently the performance on audio is not very good yet
* Swiss German translation is better now, but still behind image * Swiss German translation is better now, but still behind image
* worse than image quality * worse than image quality
* 80B audio tokens vs 850B image tokens * 80B audio tokens vs 850B image tokens
* SRF has not been used yet, will be done later * SRF has not been used yet, will be done later
* Licencing * What about generating synthetic data
### New Action Items ### New Action Items
... ...
......