Vani is a Cloud + Local Hybrid multilingual voice-to-voice assistant supporting all 22 Constitutionally Recognized Indian Languages using state-of-the-art speech and language models: 1. Cloud / Browser WebRTC Mode (Hugging Face Spaces, Mobile, Any Browser): - Streams your microphone audio directly through the browser (gr.Audio(streaming=True)). - Evaluates speech boundaries in real time via LiveKit Silero ONNX VAD. - Auto-plays crystal-clear synthesized Indic speech in your browser with 3-Layer Acoustic Echo Protection so the assistant never hears itself. 2. Local Zero-Click Hardware Mode (Windows / Desktop GPU): - Captures audio directly from your OS soundcard via sounddevice.InputStream…
Independent publisher
Saurabh Kumar
thedevsaurabh
Fine Tuning and RAG
Models in Library1
Datasets in Library0
Models on Hugging Face1
Followers—
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.