MOSS Transcribe Diarize: Accurate Transcription with Speaker Diarization
Paper • 2601.01554 • Published • 63
MOSS Transcribe
A unified multimodal large language model for end-to-end speaker-attributed, time-stamped transcription.
A unified multimodal large language model for end-to-end speaker-attributed, time-stamped transcription.
Transcribe audio/video with speaker diarization
