Chris Seymour

So the effect can be seen with guppy to a lesser extent so I don't think it's totally surprising given the improvement in quality in the latest bonito version. ![Screenshot...

This issue is coming from the parasail library which bonito uses to align the called sequence to the target sequence - I would suspect you are seeing this because your...

Thanks @btu6626 - unfortunately it would be hard to support `ppc64le` as I don't have a development environment.

@simonbrd you have set `--device cpu` not the GPU in your screenshot.

The default batch size for the fast model is 1536 and uses about ~10GB of GPU memory so try reducing the batchsize to fit your GPU memory capacity `bonito basecaller...

@simonbrd to save data in a training format you need to add `--save-ctc` when basecalling, the error message you are getting is because not training data is present in `data/train`.

Hey @JosephLalli The intention is to get kbeam on GitHub soon - we are just polishing it up.

Thanks @piaohe111 - does this help https://towardsdatascience.com/an-intuitive-explanation-of-beam-search-9b1d744e7a0f

Hi @waka45 Did this occur only on channel 507? Also can you colour by mux?

Hey @JacobHayes I can upgrade `pysam` and `requests`. Bonito doesn't use `onnxruntime` directly but it's used when calling mods _(it's a [unpinned] dependancy of remora)._ Yes, you are correct w.r.t...