Hervé BREDIN
Hervé BREDIN
Thanks! Will definitely have a look at this PR but with summer vacations coming up, I cannot promise any ETA...
Would you mind sharing a minimum reproducible example in Google Colab?
Please share a notebook on Google Colab where the error actually happens because I cannot reproduce it.
`pyannote-metrics` has some code to do that. https://github.com/pyannote/pyannote-metrics/blob/2733ef55eed2a30e1ce2c76d935f495128a693de/pyannote/metrics/cli.py#L137-L159 http://pyannote.github.io/pyannote-metrics/reference.html#pyannote.metrics.detection.DetectionPrecisionRecallFMeasure
> This would be very cool to have. Is there a pretrained checkpoint available for this somewhere? Not yet. And no ETA, unfortunately.
Apologies, I will eventually have a look it but I really don't have the bandwidth right now.
Hey @sanchit-gandhi. I understand the frustration but I am actually the sole maintainer and also have many other hats. I am doing my best but have other priorities right now...
That's strange. Looking at the diff between 3.1.1 and 3.1.0, I see no reason why this would happen: https://github.com/pyannote/pyannote-audio/compare/3.1.0...3.1.1
Thanks. 1. Comment says "improve performance using onnx". Could you please provide us with reproducible numbers? 2. Genuine question: can you please document what this change does exactly?
Thanks! Can you please add an entry in CHANGELOG.md (ideally with a link to your Github profile)?