Voice gender classifier for European voice AI (1MB, ONNX, 4ms)

Name: Voice gender classifier for European voice AI (1MB, ONNX, 4ms)
Availability: InStock
Author: biduskamil

by biduskamil·May 12, 2026·5 points·2 comments

Visit Project View on HN

AI Analysis

●●SolidNiche GemSlick

Enables grammatical gender inflection in EU voice agents with 4ms CPU inference.

Strengths

•Tiny 0.64MB model size fits easily alongside VAD in edge pipelines.
•ONNX export allows inference without PyTorch runtime dependencies.
•Addresses specific EU pain point of grammatical gender in verb forms.

Weaknesses

•Accuracy drops significantly on strong international accents (EdAcc).
•Solves a narrow preprocessing step rather than a full pipeline problem.

Post Description

Hi, I'm Kamil and I'm a founder of Applied AI agency in Warsaw, Poland.

We've trained a small <1MB voice classifier model that runs on CPU in 4ms. Can be run next to silero VAD in voice AI deployments.

What we noticed in production deployments of voice assistants in Contact Centers in EU is that human consultants pick up immediately how to inflect verbs and ajdectives after one utterance from the caller. But voice AI agents don't know it until 1-2 minutes into the call when they are either corrected or the caller uses explicitly words with male/female form a couple of times.

Our model solves this just from the first utterance of caller speech. The voice AI pipeline can inject the classification as context to the system prompt. We observed a significant impact of this on the adoption of voice AI in practice.

Model + paper: https://huggingface.co/syntropicsignal-ai/gender-voice-class...