moonshine
Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces
- 12k
- C++
- 8 d ago
Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces
Machine Learning tutorials with TensorFlow 2 and Keras in Python (Jupyter notebooks included) - (LSTMs, Hyperameter tuning, Data preprocessing, Bias-variance tradeoff, Anomaly Detection, Autoencoders, Time Series Forecasting, Object Detection, Sentiment Analysis, Intent Recognition with BERT)
TEXTOIR is the first opensource toolkit for text open intent recognition. (ACL 2021)
Xing4.0-29B-Intent - schema-guided intent recognition and structured information extraction (intent and slot filling, entity, relation and event extraction). A 29B MoE with 4B activated parameters, Apache-2.0.
Intent recognition for voice AI — 50x faster than LLM routing. Vector search + neural reranking in <100ms.
Multilingual decision engine for intents you describe in plain words, no training examples. It picks the matching intent, with a margin that flags doubtful answers; R2Intent v1 also answers yes or no (beta), with probabilities. About 26 ms per message on a GPU (compiled). Python, HTTP or MCP, self-hosted. Library Apache-2.0; models CC BY-NC 4.0.
Text classification model, used with transformers.