🚀 Introducing HVC-Audio-Convert by Hibernates!
huggingface.co/Hibernates/HV…
This cutting-edge voice conversion model combines SoftVC feature extraction with the powerful VITS architecture, delivering unparalleled voice transformation. Pre-trained on diverse, multi-speaker datasets, it supports high-quality, cross-lingual voice conversion—perfect for breaking language barriers and creating seamless, natural-sounding audio.
Whether for media production, accessibility, or next-gen voice tech, HVC-Audio-Convert is redefining what’s possible in voice synthesis. 🎙️✨
#AI#VoiceTech#Innovation#Hibernates#AudioConversion
I have some timecoded transcriptions where the timecodes drift away from the audio (audioconversion we did not keep track of?). Any tips how to rematch them? Measure the drift at the end and progressively stretch the timecodes to match? @DingemanseMark@chbergma 1/2