🏗️ Building on HF

Siddh Jagani

SiddhJagani

8 61

AI & ML interests

Building local AI systems, LLM tools, RAG infrastructure, and MLX model deployments.

Recent Activity

liked a Space about 1 month ago

huggingface/InferenceSupport

updated a Space 3 months ago

SiddhJagani/claude

liked a model 3 months ago

ai4bharat/indic-parler-tts

View all activity

Organizations

liked a Space about 1 month ago

InferenceSupport

💥

631

Discussions about the Inference Providers feature on the Hub

liked a model 3 months ago

ai4bharat/indic-parler-tts

Text-to-Speech • 0.9B • Updated Sep 24, 2025 • 252k • 283

liked a Space 3 months ago

Huggingface User Stats

💻

fetch hf user stats

liked a Space 4 months ago

See-through: Layer Decomposition

🔍

141

Generate layered PSD of anime characters from a single image

liked 3 Spaces 5 months ago

LFM2 WebGPU – In-browser tool calling

🛠

In-browser tool calling, powered by Transformers.js

WebSearch Chat

🌐

Ask ERNIE-4.5, with built-in web search.

LFM2.5 1.2B Thinking WebGPU

💧

125

Run LFM2.5-1.2B-Thinking directly in your browser on WebGPU

liked 3 Spaces 6 months ago

Seed Voice Conversion

🎤

507

Convert speech to another voice instantly

LuxTTS

🚀

110

Space for LuxTTS: a 150x realtime voice cloning TTS model

SmolVLM Realtime WebGPU (Vue)

👀

Yet another WebGPU based SmolVLM, re-implemented in Vue

liked 4 models 7 months ago

liked a Space 7 months ago

Voice Agent

⚡

An agent that convert speech to text and text to speech

liked a model 7 months ago

bartowski/agentica-org_DeepScaleR-1.5B-Preview-GGUF

Text Generation • 2B • Updated Feb 11, 2025 • 3.98k • 41

liked 3 Spaces 7 months ago

Livekit Assistant

🏃

Backend for my Livekit Assistant

Mediapipe Face Mesh

😻

Detect and visualize facial landmarks on photos

Paper2Poster

🚀

Create a conference poster PDF from your paper