原帖引用 · 原文
Rohan Paul@rohanpaul_ai
@hume_ai big step for machine listening.
a text-only pipeline can’t answer these, because the mismatch only exists between what was said and how it was said.
Introducing the Hume Audio Decision API.
Ask anything: How many speakers? Is anyone laughing? Is the caller frustrated?
What used to take 10+ models is now one call.
Trained on 10M+ human judgments, so it answers the way human listeners would.
Realtime, or across hours of recordings.
Request access below.
在 X 查看这条帖子 ↗
· UTC+8