“Obviously, we had to put kind of both like a pre-training…” — Practical AI at 37:49
“Obviously, we had to put kind of both like a pre-training data set in audio and in text. Initially, we had to put the text data set together also because there wasn't necessarily at the time an alternative that we could use in terms of license. And also, we wanted to be able to keep training both on text and audio so…”
0:00
50:03