Smart Turn
AI
audio turn detection model
SHOW HN2025
How HN took it
7 positive, 7 neutral or asking, 0 mixed, 1 critical, out of 15 comments about the project. Thread score +0.37.
Idea: 5 for, 0 againstDesign: 2 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Model is well documented and the README is clear
From 1 comment
I got most of my answers from the README. Well written. I read most of it. Can you share what kind of resources (and how much of them) were required to fine tune Wav2Vec2-BERT?
foundzen on HN
Architecture matches existing turn-based models
From 1 comment
Having reviewed a few turn based models your implementation is pretty inline with them. Excited to see how this matures!
written-beyond on HN
Important problem for voice agents
From 1 comment
I'm excited to see this particular technology developing more. From the absolute worst speech systems such as Siri, who will happily interrupt to respond with nonsense at the…
xp84 on HN
Objections
Turn detection may not be solvable without push-to-talk
From 1 comment
I will have a look at this. Played with pipecat before and it's great, switched to sherpa-onnx though since I need something that compile to native and can run on edge devices.…
pzo on HN
Model could interrupt users inappropriately
From 1 comment
... but will the model learn when to interrupt you out of frustration with your ongoing statements, and start shouting? it seems like for the obvious use-cases there might need…
meltyness on HN
Requests
Support for multiple speakers
From 1 comment
Does this support multiple speakers?
lostmsu on HN
Better SEO and explanation of the term turn detection
From 1 comment
Re SEO, I note "utterance" only occurs once, in a perhaps-ephemeral "Things to do" description. To help with "what is?" and SEO, perhaps something like "Turn detection (aka…
mncharity on HN
Questions
What is turn detection?
From 1 comment
Ok what's turn detection?
remram on HN
How many parameters does the model have?
From 1 comment
As an [diagnosed] HF autistic person, this is unironically something I would go for in an earpiece. How many parameters is the model?
zamalek on HN
What resources were needed to fine tune the model?
From 1 comment
I got most of my answers from the README. Well written. I read most of it. Can you share what kind of resources (and how much of them) were required to fine tune Wav2Vec2-BERT?
foundzen on HN
Alternatives named
sherpa-onnx
From 1 comment
I will have a look at this. Played with pipecat before and it's great, switched to sherpa-onnx though since I need something that compile to native and can run on edge devices.…
pzo on HN
LiveKit text-based turn detection model
From 1 comment