WWW
As a researcher/machine learning engineer looking for solutions to do voice conversion I would like to understand AudioLM as a possible candidate for voice conversion.
AC
Try and understand the code and the paper. Next follow-up to this would be to understand its feasability for voice conversion either using Torgo or UASpeech, or compare other models like SpeechT5.
WWW As a researcher/machine learning engineer looking for solutions to do voice conversion I would like to understand AudioLM as a possible candidate for voice conversion.
AudioLM was released by Google sometime in 2020: https://google-research.github.io/seanet/audiolm/examples/
There is one known open source implementation that might be worth playing around with : https://github.com/lucidrains/audiolm-pytorch/tree/main/audiolm_pytorch this code comes with a colab demo.
AC Try and understand the code and the paper. Next follow-up to this would be to understand its feasability for voice conversion either using Torgo or UASpeech, or compare other models like SpeechT5.