Samuel Larkin

Hi, not sure if I'm using the minimalist command line but this fails ``` marian-decoder \ --input=test-dedup/source \ --models=model/model.npz \ --vocabs=vocab.iu.json,vocab.en.json \ < test-dedup/source Error: Expected at least 1 arguments...

Thanks for the quick response! I should've RTFM more carefully ;) as it is clear that the infoRenderer is not a string. I wrote a new solution where in the...

My answer was getting a bit long, so I decided to make two comments instead. I was unable to get my other solution to work. Here are the modifications that...

I should document my solution I turns out that my input is not arpabet but when I call `preprocess.py` it marks my text in curly braces signifying that it is...

FYI I would like to point out that I'm not an expert. I'm new at TTS and I'm still learning. 1. I still want to train on phoneme. 2. I...

Are you using your own symbols? Check issue #66 because I had the same problem of shape mismatch. The `mfa` part is good, the problem is that some processing is...

Looks like it is related to: - https://github.com/pytorch/pytorch/issues/69894 - https://github.com/pytorch/pytorch/pull/69823

Solution for now: I downgraded `setuptools` to `setuptools=58.0.4=py38h06a4308_0` doing `conda install -c anaconda setuptools`.

The error message is misleading because the stack trace shows `add-deltas` and `apply-cmvn` but in reality, if we run the command the first part of the command `apply-cmvn.... | add-deltas`...

I've been trying to debut this and I found some hint. I have several wav files, more than 10. If I run the trio of commands that fail, it looks...