Leszek Pryszcz

same here v 25.2.2

ok, I've solved it by replacing `extensions/python.el` with the version from https://github.com/emacs-mirror/emacs. [The error is due to changes in emacs introduced in 2013](https://lists.gnu.org/archive/html/emacs-diffs/2013-09/msg00005.html). You can get it also from my...

Hi, as far as I understand it, the model doesn't return sequence, but scores that need to be decoded. This should work: ```python scores = model(inputs) seqs = model.decode_batch(scores) ```...

Hi, I'm only using `fast` models. We're developing an app and providing only CPU-mode should be enough for our use cases (and cheaper to deploy for end users :) ),...

so I've edited `koi/ctc.py` - commented out `assert Ms.device.index is not None` - and replaced `Ms.device.index` with `Ms.device.index if Ms.device.type=='cuda' else None` and it was executing on CPU, but there...

I'm also interested in this feature!

This PR is still not merged. Meanwhile, just execute before build: ``` rm fastdtw/*.cpp ```

Hi, you can either use: - [fast5mod](https://github.com/nanoporetech/fast5mod) - it's deprecated - [megalodon](https://github.com/nanoporetech/megalodon) - it didn't work with our custom-trained RNA models - [modPhred](https://github.com/novoalab/modPhred) - should work with custom-trained DNA/RNA models...

actually, creating empty `.cpp` files is enough to build the package. ```bash touch tombo/_c_dynamic_programming.cpp tombo/_c_helper.cpp pip install -e . ```

Dear @bishopia , thanks for the interest in redundans. As for your question, the accuracy of your read doesn't matter that much for redundans scaffolding (it should work with reads...