@AdinaY on Hugging Face: "MOSS Transcribe Diarize 🔊 A multimodal model for Speaker-Attributed…"

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

AdinaY

posted an update 3 days ago

Post

508

MOSS Transcribe Diarize 🔊 A multimodal model for Speaker-Attributed, Time-Stamped Transcription from OpenMOSS.

MOSS Transcribe Diarize: Accurate Transcription with Speaker Diarization (2601.01554)
OpenMOSS-Team/MOSS-transcribe-diarize

✨ Single-pass end-to-end SATS
✨ 128k context, ~90 min audio
✨ Robust to overlap & noise

zainikhan12

2 days ago

MOSS Transcribe Diarize delivers accurate, speaker-attributed, time-stamped transcription, showcasing the power of multimodal models in real-world audio understanding. https://agahi.weeb.pk/

In this post

AdinaY Adina Yakefu
zainikhan12 zainiahmad