hugpadhugpad

ACE-Step / acestep-transcriber

Audio11B1.3K66Updated Feb 3, 2026
Hugging Face

Downloads

1.3K

Likes

66

Last updated

Feb 3, 2026

License

mit

ACE-Step Transcriber is the annotation model used by ACE-Step v1.5 for training data labeling. It is a powerful multilingual audio transcription model capable of transcribing both speech and singing voice with high accuracy.

Tasks & library

  • audio text to text
  • transformers

Tags

  • transformers
  • qwen2_5_omni
  • text-to-audio
  • music
  • audio
  • audio-text-to-text

Technical specifications

Parameters11B
Librarytransformers
LanguagesNot available
Licensemit