An update to my previous post on using Python to batch analyze audio files.
I’ve added a featured that checks for the presence of ‘audiobook.xml’ in the parent to the current working directory. If found, the script parses out the book author, title and ISBN for inclusion in a document header.
I’m happy with the output and formatting of the document. If you print as PDF using the macOS print dialog you get a … Read the rest “Demo of Audio Log File Generator”
Earlier this year I collaborated with Toronto software start-up Dessa to produce a text-to-speech model with Joe Rogan‘s voice. Joe thought it was pretty trippy!
Can you tell real from fake? Try the blind test at: https://fakejoerogan.com/
Dessa published a rundown of the process in two parts on Medium:
Part 1:
RealTalk: This Speech Synthesis Model Our Engineers Built Recreates a Human Voice Perfectly
Part 2:
RealTalk (Pt. II): How We Recreated Joe Rogan’s … Read the rest “Joe Rogan Voice AI”
I’ve been consulting with Toronto machine learning startup Dessa on an exciting audio based project. (more on that when the time is right)
The he engineers there have impressed me with what they’ve been able to accomplish in terms of analyzing and processing audio despite their inexperience working with audio in general. The experience has inspired me to get my feet wet with Python, the very popular and accessible programming language.
One of the best … Read the rest “Python the Hard Way”
Recent Comments