hawaiicoco/slotvox
End-to-end spoken language understanding toolkit: a small trainable neural audio codec with RVQ, joint intent-and-slot models over speech features, streaming partial intents, a speech-LLM instruction data pipeline, and turn-level evaluation with reproducible reports. NumPy core with a CPU-only torch extra; synthetic data only, fully offline.
GitHub repository with 36 stars and 243 forks.
Language: Python
Topics: end-to-end, instruction-data, intent-detection, neural-audio-codec, numpy, python, pytorch, slot-filling, speech-language-model, spoken-language-understanding