Relationship Extraction from NARrative Documents
Run 23 speech language models on your own audio task through one interface: vLLM, transformers, and API backends behind a single JSONL contract. Ships HEAR, the speaker-attribution benchmark from our EMNLP 2026 paper.
Speaker-attributed transcripts with Parakeet-tdt-v3 and Pyannote.audio LiteRT.
面向Android 平台的纯 Java 中文小说对话、旁白、内心独白的识别分离工具
在 Mac 电脑上制作多角色有声书 | Multi-voice audiobooks, made on your Mac
Speaker Attribution Graph: production-shaped framework for tracing audio, transcript, and optional video evidence into speaker-attribution decisions.
Reliable Discord voice recording and speaker-attributed transcription, with durable recovery and local Faster Whisper processing.A streamlined stack for Discord audio capture, transcription, and text deduplication.
Extract Facebook Messenger, Viber, and audio evidence into a normalized sender/receiver CSV using OCR, MOSS, and Ollama.
To associate your repository with the speaker-attribution topic, visit your repo's landing page and select "manage topics."