ValueError: No valid path is found for training.

[enorrmann]

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

[MSDNAndi]

I ran into the same problem. I needed to have two different pairs of files (.wav and .txt) to make it work.

[enorrmann]

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

[constan1]

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.

I ran into the same problem. I needed to have two different pairs of files (.wav and .txt) to make it work.

[Annoytanor]

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.

[constan1]

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?

[kaaancan]

I figured out the issue after some debugging with the help of chatGPT. Its actually super stupid and simple 🤦

You need to provide 2 audio and 2 normalized.txt samples

[RinLovesYou]

I have provided two audio files and two normalized txt, i still get no valid path is found for training