NVIDIA / tacotron2

Tacotron 2 - PyTorch implementation with faster-than-realtime inference
BSD 3-Clause "New" or "Revised" License
5.11k stars 1.39k forks source link

INFERENCE ISSUE #585

Open A-d-DASARE opened 1 year ago

A-d-DASARE commented 1 year ago

I think whoever tries to install dependencies now afresh with tf1, it does not work, As google has removed it support for tf1 version. Luckily if you have created conda environment for tf1 you can still train your model on local machine. But the problem is for inference part. When i try running the Jupyter notebook in the same conda environment which uses tf1 for training, it throws something called internal error. Now my model is trained and stored in zip format in outdir. But i am unable to check inference. Could someone help me in this regard. Any lead is highly appreciated. Thanks in advance.