Praveen Narayanan

icon indicating a website link pravn.wordpress.com icon indicating an email [email protected]

icon location Montreal, Canada icon location Machine learner and parallel computing enthusiast. I work in Bird's Eye View Modelling in the context of autonomous vehicles.

Results 4 comments of Praveen Narayanan

Sample Trainer and Decoder for this

Yes could you put up data and main file, please? It would be quite useful.

How to use dvector_create.py

I have a workaround for the wav creator for TIMIT, which I have put up in my forked repo. https://github.com/pravn/PyTorch_Speaker_Verification/blob/master/VAD_segments.py In VAD create, for TIMIT, it can complain that the...

Speech Tools wrongly named as .tar.gz

This only happens if we download speech_tools as mentioned in the voice conversion wiki page under "Dependency Tools". https://github.com/CSTR-Edinburgh/merlin/tree/master/egs/voice_conversion/s1 I was able to get around this by using the install...

BEVFusion: Wrong pytorch model/keys missing or misaligned while running 'demo'

I got the keys to align by hacking it. Load checkpoints and replace vtransform with view_transform to make it work. However, @hepingpeace notes, the boxes produced are incorrect. ![demo](https://github.com/open-mmlab/mmdetection3d/assets/550741/e6537308-2a45-4b52-9859-8a4436ed807e) Using...