Richard Harris
Richard Harris
Thanks for the update @sonalhenson, If you're still able to use the problematic GPU queue, could you please generate the verbose logs so that we can gather more details for...
@sonalhenson, this error relates to not being able to connect to the ONT CDN to download models. ```text [2025-10-16 14:19:57.123] [info] - downloading [email protected] with httplib [2025-10-16 14:19:57.199] [error] Failed...
Any updates on this issue?
Hi @ma851tos, Can you please try reducing the `--batchsize`? I can't see the batchsize that was selected by default in your logs to give you a recommendation - Did you...
Hi @ma851tos, Apologies for the delay - Do you make any progress without modbases? How much data are you processing here?
Dorado is **heavily** optimised for CUDA GPUs as these are the devices we put in our sequencing hardware. I'd say 5x slower on MacOS is not unexpected here. I see...
We're always working on performance improvements in Dorado and we keep an eye out for opportunities such as those offered MTL4. I believe this issue is now resolved. Thanks for...
Hi @uribertocchi, It's unusual to have to edit the pod5 files to restore missing metadata after recovery - this suggests there might be more missing metadata which has corrupted the...
Could you also try to recover each file separately - there may be an issue recovering multiple files at once.
@uribertocchi, It's possible that when moving the original files some of the temporary hidden files were missed. The temporary files which contain the partial read metadata, start with a dot...