Tips for train syncnet about dinet

[KimGyeongsu]

I used initial learning rate as 1e-5!

[KimGyeongsu]

For all stages, I used 1e-5.

[won-bae]

Hi thanks for sharing the tips!

May I know the learning rate you used eventually? I guess many people including myself have limited computation to tune it multiple times. It would be greatly helpful if you can share it!

Thank you

[won-bae]

Thank you for your quick reply!
Sorry but did you use 1e-5 only for clip or for every stage of frame training?

[won-bae]

Thanks for sharing that!

[FacePoluke]

Did you train SyncNet from scratch or use the provided pre-trained model? Also, I thought SyncNet only had a clip mode, but in your above response, it seems like there is a frame mode mentioned.

[KimGyeongsu]

Similar to dinet training code that author provided, I trained syncnet from scratch.
For frame stage, audio feature should be deepspeech featrue from [n-2:n+3], if we use n th frame as face feature.

[xiao-keeplearning]

Hello, I also have a question. How can we determine whether the model has converged during the training process of DINet?