zxkane / audio-transcriber Star 7 Code Issues Pull requests Agent skill for multi-speaker meeting & podcast transcription — FunASR (Paraformer/SenseVoice/Whisper) + MiMo-V2.5-ASR + CAM++ speaker diarization + LLM cleanup. 99 languages, GPU & CPU. Works with Claude Code and any SKILL.md-compatible agent. multilingual speech-to-text whisper asr speaker-diarization meeting-transcription paraformer funasr claude-code xiaomi-mimo claude-plugin claude-code-skill agent-skill podcast-transcription openclaw clawhub chinese-asr interview-transcription mimo-asr multi-engine-asr Updated May 1, 2026 Python
JsonBorn98 / VideoCaptioner Star 0 Code Issues Pull requests 个人使用为主、按需更新的 VideoCaptioner fork:MiMo/Qwen 转录与对齐、双 LLM 翻译校对、字幕后处理和 FFmpeg 导出。 python cli ffmpeg pyqt5 video-processing speech-to-text hardware-acceleration asr forced-alignment subtitle-generator subtitle-editor subtitle-translation video-subtitles qwen-asr mimo-asr Updated Jul 25, 2026 Python