hugpadhugpad

sbintuitions / hikari-medium

Audio764M1741Updated Oct 26, 2026
Hugging Face

Downloads

174

Likes

1

Last updated

Oct 26, 2026

License

mit

Hikari-medium is a streaming speech-to-text translation and transcription model. It emits text incrementally while the speaker is still talking, without waiting for the utterance to finish.

Tasks & library

  • automatic speech recognition
  • transformers

Tags

  • transformers
  • hikari
  • speech-translation
  • simultaneous-translation
  • streaming-asr
  • whisper

Technical specifications

Parameters764M
Librarytransformers
Languagesen, ja, ru, de
Licensemit