Ruthvicp

Make sure you have set the corpus path in docker-compose.yml. Also I assume you have tried using 'english_corpus_no_dups.csv', it has an empty line because of which you have that error....

I have good alignment from 30k to 250k steps on a dataset of 18 hours (English). As mentioned in the issue, I do have good audio(natural sounding) with every step...

Create a virtual environment and activate it. Then try "pip install -r requirements.txt"

I have used a different dataset (private) and trained for 18k steps using the existing mimic2 (master branch). I was able to get good alignment and also a decent voice....