Downloads · 30 days
0
Assesment_SR-model
Saalil/Assesment_SR-model
Assesment_SR-model is a audio classification model from Saalil. Use it for the audio classification task on the model card, and read the license before you ship it in a product. It is set up for onnx. The card lists the license as apache-2.0.
Audio-native complete/incomplete classifier built for the Shiprocket assignment.
Access
Public
Updated Aug 21, 2026
Repo size
72.4 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx40.4 MB · 56%
At a glance
- Task
- Audio Classification
- Library
- onnx
- License
- apache-2.0
- Access
- Public
- Created
- Aug 21, 2026
- Updated
- Aug 21, 2026
- SHA
- 8807fff8
Spaces
Model card
From the Hugging Face model README
Shiprocket Turn Detection
Audio-native complete/incomplete classifier built for the Shiprocket assignment.
Intended use
Run after VAD detects a pause. Input: up to 8 seconds of 16 kHz mono audio. Output: P(complete).
Training data
Only pipecat-ai/smart-turn-data-v3.2-train. Indic results use official Hindi/Marathi slices.
Limitations
- Not a full-duplex conversational model.
- Clip metrics do not prove live interruption quality.
- Browser preprocessing is approximate; use the Python path as reference.
- Do not use for safety-critical barge-in.
Metrics
Fill after the first trained export. Until then the demo may fall back to Pipecat Smart Turn v3.2.
- Task
- Audio Classification
- Library
- onnx
- License
- apache-2.0
- Languages
- multilingual
- Created
- Aug 21, 2026
- Updated
- Aug 21, 2026