---
language:
- en
- hi
license: mit
library_name: onnxruntime
pipeline_tag: audio-classification
tags:
- turn-detection
- endpointing
- voice-ai
- whisper
- hinglish
datasets:
- pipecat-ai/smart-turn-data-v3.2-train
metrics:
- accuracy
- roc_auc
---

# Voice Turn Detection

This audio classifier estimates whether a speaker has completed a conversational turn. It is trained for English, Hindi and Hinglish speech and does not require transcription.

[Live demo](https://vedantshelkar--voice-turn-detection-web.modal.run) | [Source code](https://github.com/vedants254/Voice-Turn-detection)

## Model

The model keeps the Whisper Tiny encoder, trims its positional context to eight seconds, pools the 400 encoder frames with learned scalar attention and predicts one completion logit through a small MLP. The exported ONNX graph includes log-Mel extraction and returns a sigmoid probability.

## Input and output

- Input name: `waveform`
- Input shape: `[batch, 128000]`
- Input format: mono float32 PCM at 16 kHz
- Output name: `p_complete`
- Output shape: `[batch]`

Keep the latest eight seconds. Left-pad short audio with zeros so the newest sample stays on the right edge.

## Evaluation

The frozen model was evaluated on all 9,104 English and Hindi clips in `pipecat-ai/smart-turn-data-v3.2-test`.

| Slice | Clips | Accuracy at 0.5 | ROC AUC |
|---|---:|---:|---:|
| Overall | 9,104 | 93.70% | 0.9826 |
| Hindi | 1,284 | 93.93% | 0.9853 |
| English | 7,820 | 93.66% | 0.9820 |
| Real speech | 5,367 | 94.37% | 0.9862 |
| Synthetic speech | 3,737 | 92.72% | 0.9766 |

## Limits

The training data is synthetic-heavy and the model is limited to the speech conditions represented in that dataset. Calibrate the threshold on deployment traffic. A higher threshold reduces interruptions but increases response delay.