raws84

Thanks Molian, you are right. I also figured this out. For me Librosa 0.9.2, numpy 1.23.5 and Tensorflow 2.12.0 worked while running python 3.9.16

There is also some minor error in how utils is called in one of the colab files.. It should be import util.utils as util. Other wise its pretty good.

Make sure you install the correct version of dependencies as specified in the requirements file. Create a virtual environment with python3.7, then install ffmpeg and py torch and then the...

I think its a librosa version issue. Install the following in colab before running the code and it should work !pip install unidecode !pip install webrtcvad !pip install librosa==0.8.1

I think its a librosa version issue. Make sure you create a virtual environment with python3.7 and then install ffmpeg, torch, and then the requirements in that order. Specifically make...

install librosa==0.8.1 as mentioned in the requirements document. Ideally create a virtual environment with Python 3.7 then install ffmpeg, pytorch and then the requirements in the environment and then run...

you can try installing unidecode pip install unidecode I would suggest if you already haven't then create a virtual environment with python3.7 and then activate it. Following that install ffmpeg,...

Hi Moein, It looks like there is some difference in keys in the saved model and model architecture. While using the infer file, I am getting the following error. Any...