22degrees

Thanks for looking into this so quickly! I'll try this out. It's not ideal - I'll have to explain the magic config file, but it's a better workaround than mine,...

Maybe this is a problem with how pip/pypi works. The dependency graph should be solvable without downloading ANY packages through pypi exposing some small file(s) or api. I think it...

I'm ok with sacrificing "total locking" guarantees, as some of the locking is done by pinning a docker base image. Thanks for the new workaround, but I don't think would...

> So maybe we can update our cache file with data from those sources. If we do, I don't know if it should be done by default, as it has...

Since this a an edge case relevant to my docker workflow, I'll post my docker workaround: create a docker cache for the pip cache: ``` RUN --mount=type=cache,target=/root/.cache/pip python3 -m piptools...

I am having the same issue, where the checkpoint audio sounds great, alignment looks great, but audio from eval and demo_server are just noise. I thought it could be overfitting,...

For reference, here's an alignment graph generated during training.  and the audio from training and evaluation: [audio_clips.zip](https://github.com/keithito/tacotron/files/2520553/audio_clips.zip) The input text is the same for both. Perhaps it has to...

In case anyone else is having similar issues, I re-read the paper and assume the author here did the same: > During training, we always feed every r-th ground truth...