|
|
|
|
|
|
by YeGoblynQueenne
1046 days ago
|
|
|
>> They've already produced Whisper for audio-to-text, and image-to-text is underway. Two modalities down. Another couple hundred to go. Unfortunately we're fast running out of the modalities that neural nets have shown capability in (image, text, sound... I think that's it). |
|
|