TensorSpeech / TensorFlowTTS

:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)
https://tensorspeech.github.io/TensorFlowTTS/
Apache License 2.0
3.84k stars 815 forks source link

Preprocessing error with ljspeech #786

Closed LxtteDev closed 1 year ago

LxtteDev commented 1 year ago

When preprocessing, I am getting a new error: ValueError: numpy.ndarray size changed, may indicate binary incompatibility. Expected 96 from C header, got 88 from PyObject. I dont think the error has nothing to do with an amount of files. I removed some .wav's and also tried adding some to no avail. I am using the preprocess\ljspeech_preprocess.yaml config and ljspeech dataset.

ahmedalbahnasawi commented 1 year ago

what version of numpy you using? i think upgrading numpy would solve the issue.

LxtteDev commented 1 year ago

I am using numpy 1.21.6 but I dont want to upgrade because I am using tensorflow 2.6. If I upgrade, tensorflow also gets upgraded.

LxtteDev commented 1 year ago

I tried upgrading it. Nothing changed. Still getting the same error.

ahmedalbahnasawi commented 1 year ago

pip install TensorFlowTTS==1.8 i am using tf-gpu 2.6 and numpy 1.19.5. let me know if it works ?

DannyP0 commented 1 year ago

@LxtteDev use pyworld < 0.3.2, e.g pip install pyworld==0.3.1

stale[bot] commented 1 year ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs.