Can Gemini transcribe a song?
Gemini 4 Argon → https://g.dev/ai/gemini-about Google Gemini models → https://g.dev/ai/gemini-models-docs Watch the full episode → https://g.dev/youtube/gemini-models-full In this video, Luke Schlangen and Mollie Pettit team up with fellow Googler Gabe Weiss on a classically difficult problem in audio machine learning: transcribing a multi-instrument, polyphonic audio track into playable sheet music. Watch as they throw it at three different Gemini models (Gemini 3.5 Flash-Lite, Gemini 3.8 Flash, and the new Gemini 4 Argon) and listen to Gabe play the results on the mandolin. Chapters: 0:00 –
Discussion
Rejoignez la communauté pour réagir et poser vos questions.
Aucun message pour l'instant. Lancez la discussion !