search

NVIDIA / flowtron

Flowtron is an auto-regressive flow-based generative network for text to speech synthesis with control over speech variation and style transfer
https://nv-adlr.github.io/Flowtron
Apache License 2.0
887 stars 177 forks source link

Train on German Language #124

Open philpln opened 3 years ago

philpln commented 3 years ago

Hello, I'm trying to train on the Mozilla Common Voice German Dataset and don't know how to update the filelists inside the filelists folder to point to the Common Voice Dataset. I don't know if this is the right place to ask this, but I can't find anything online on how to do it. Thanks in advance, Phil

Muhyzater commented 3 years ago

Hello @C4rb0ngit, I am not sure if I understand the question correctly, but what I have in mind is that you should have your files (PSV files) in the following format:

path_to_wav_file|text of the wav|speaker_id

and then edit config.json, specificallytraining_files and validation_files lines to point to the aforementioned files.

micsoundsnice commented 3 years ago

hi, i am trying it too. Did you get any results? I managed to start training but the results are "kauderwelsch"

philpln commented 2 years ago

hi, i am trying it too. Did you get any results? I managed to start training but the results are "kauderwelsch"

I didn't but I didn't work on it for a couple of weeks. If you want, add me on discord maybe we can help each other. PhilPhil#5241