ONNX (Open Neural Network Exchange) is an open format for representing machine learning models, allowing models to be transferred between different frameworks and tools.
Why this server?
Utilizes bundled ONNX embeddings for semantic code search capabilities that work offline without requiring API keys.
Why this server?
Utilizes ONNX model files for text-to-speech processing, specifically loading the Kokoro model weights for voice generation.
Why this server?
Uses the ONNX runtime to run the Kokoro TTS model, enabling high-quality text-to-speech conversion without requiring an API key.
Why this server?
Supports ONNX model format for AI accelerator inference workloads including MemryX MX3, Coral TPU, Hailo-8, and Intel NCS2.
Why this server?
Uses ONNX runtime for the Kokoro neural voice models, providing high-quality text-to-speech synthesis with multiple voices and emotional expressions
Why this server?
Utilizes local ONNX models for efficient, zero-config semantic search and document embedding generation.
Why this server?
Uses the ONNX Runtime via FastEmbed to provide local, free semantic search capabilities without external API dependencies.
Why this server?
Utilizes ONNX runtime for local embedding model inference, enabling efficient semantic search without external API calls.
Why this server?
Supports exporting YOLO models to ONNX format for compatibility with different runtime environments