Moritz

icon location Leipzig icon location Generative AI, NLP, and Computer Vision. Worst webdev you know.

Results 2 comments of Moritz

changed nn.Tanh() output layers to nn.Sigmoid()

Had the same issue with the VanillaVAE out-of-the-box when converting first iteration samples to a PIL Image. Commenting to bump this up.

Pyannote is 10 times slower than WhisperX with GPU utilization 10%: expected behavior or misconfiguration?

+1 for this issue thanks for the note @chubin , I have used your solution with ``` io = Audio(mono='downmix', sample_rate=16000) waveform, sample_rate = io("audio.mp3") diarization = pipeline({"waveform": waveform, "sample_rate":...