what is the present inference for generating 10sec audio using vocoder?

[saibharani]

I want to know the general inference time of generating 10sec audio using the vocoder presently i don't have the setup to test it on my own can anyone help
thank you

[tiberiu44]

Hi @saibharani ,

You can use this Notebook to run your tests: https://colab.research.google.com/drive/1cws1INmucRJ702eV4sKNJHzMDvrkg_lh

You don't need any local setup, just open the notebook in "playground mode". The code will display the inference time - it will actually take longer, because the code loads the models every time.

For 10s of audio, it should take about 5 seconds on whatever Google Collaboratory uses and about 2.5 seconds on a GTX 1080.

[saibharani]

thanks for the immediate response i will check the above link and get back if needed.
thanks again