(Realtime) Temporal Convolutions in PyTorch

Streamable Text-to-Speech model using a language modeling approach, without vector quantization

Dual-model speech AI toolkit for speaker verification and speaker-aware diarization, with streaming inference, meeting analysis, long-audio monitoring, and speaker-bank integration.

Pure PyTorch + 🤗 Transformers reimplementation of Megalodon (CEMA + chunked attention) - readable, hackable, no CUDA kernels required

Open ML systems platform for training, profiling, evaluating, and serving AI models.

Don't Think It Twice: Exploit Shift Invariance for Efficient Online Streaming Inference of CNNs

Production AI Agents for enterprise automation — 8+ specialized agents using LangChain, OpenAI function calling, and FastAPI. Multi-agent orchestration, tool use, planning loops, guardrails.

Fraud Detection AI Co-Pilot — ensemble XGBoost + Isolation Forest with 650+ features, SHAP explainability, UMAP clustering, GenAI reports via Amazon Bedrock.

CPU-native inference runtime. Local-propagation paradigm: the active region pays the cost, not the field. Bit-exact across architectures. Validated for streaming anomaly detection and audio VAD.

Streaming version of S4ND-U-Net