search

mravanelli / SincNet

SincNet is a neural architecture for efficiently processing raw audio samples.
MIT License
1.14k stars 263 forks source link

How do I run the trained model file #8

Closed sivagururaman closed 6 years ago

sivagururaman commented 6 years ago

@mravanelli I have completed the training with my own dataset. Now I wanted to use the trained model to make predictions with wav files. How do I get the prediction? Can you please help?

Thanks! Sivam.

mravanelli commented 6 years ago

You can take a look into the predictions by looking the following pred vector (pred=torch.max(pout,dim=1)[1]( in the speaker_id.py

sivagururaman commented 6 years ago

Forgot to update. I was able to get the prediction running.

Thanks!

On Sat, 13 Oct 2018 at 1:18 AM Mirco Ravanelli notifications@github.com wrote:

Closed #8 https://github.com/mravanelli/SincNet/issues/8.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/mravanelli/SincNet/issues/8#event-1901563630, or mute the thread https://github.com/notifications/unsubscribe-auth/AmZiiBdaRfCF17BV4YwLcQ-cUXufZrwCks5ukPIigaJpZM4XUf4m .

-- Regards, Sivam.