Jakub Piotr Cłapa

Hey @tmbdev, is this something you'd consider merging at some point? I could spend some time to fix the tests and incorporate any suggestions you might have.

Yeah, that would be a nice idea although you pointed out correctly that language switching is going to be challenging. We could try to train a model that would detect...

Yeah, that sounds nice. I’d like to move away from the `lang=` parameter but we could use this auto detection if there are no tags in the text.

I have no opinion on any particular library for sound files but I think: 1. We want this to work out of the box on Windows and Linux/Mac 2. We...

Hey, thanks for explaining this. So it would look like we should check if we can add `soundfile` to our dependencies to make sure it gets installed on Windows.

Hey, nice job finding all that info. I was not aware of the history behind the torchaudio backends! I agree with your conclusion - I’ll test a fresh Linux install...

Not something working out of the box I think. But I tried to keep the pipeline.py simple so it’s easy to copy and customize. Have you tried looking how it...

Yes, you're right. In the code you pointed out we assume padding is always from the right and the rest of the code allows for randomized padding. I think it...

Hey, this is a bit confusing right now, sorry. The current version of the scripts assumes that the shards will have `-audio-` in their names somewhere and this is going...

You can configure the PyTorch loss function to take log of targets or just targets. By default the targets are not in log-space and so this is what I used....