-
Notifications
You must be signed in to change notification settings - Fork 417
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
ValueError: No valid path is found for training. #93
Comments
I ran into the same problem. I needed to have two different pairs of files (.wav and .txt) to make it work. |
thank you that did the trick |
Hello. What do you mean by two different pairs of files? I have the .qnt.pt and phon.txt and normalized.txt and wav files under my directory data/librosa the config files are config/librosa with the ar.yml.
|
Your phenome files need to have between 10 and 50 phonemes in them. Try using shorter audio clips, even 10 second clips can be too long. |
My training samples are longer usually. I increased the max_phon = 5000. Would this reduce performance? |
I have provided two audio files and two normalized txt, i still get no valid path is found for training |
I followed the instructions for "test" folder
when I try to run
python -m vall_e.train yaml=config/test/ar.yml
running on linux and my files are
.
├── config
│ ├── LibriTTS
│ │ ├── ar-quarter.yml
│ │ ├── ar.yml
│ │ ├── nar-quarter.yml
│ │ └── nar.yml
│ └── test
│ ├── ar.yml
│ └── nar.yml
├── data
│ └── test
│ ├── test.normalized.txt
│ ├── test.phn.txt
│ ├── test.qnt.pt
│ └── test.wav
my ar.yml is
data_dirs: [data/test]
model: ar-quarter
batch_size: 1
eval_batch_size: 1
save_ckpt_every: 500
eval_every: 500
max_iter: 1000
The text was updated successfully, but these errors were encountered: