Omnilingual ASR 1B CTC (int8 ONNX, sherpa-onnx), mirrored for Rostrum

Meta's Omnilingual ASR 1B CTC model (speech recognition for 1,600+ languages), as the int8 ONNX export made by the k2-fsa sherpa-onnx project.

This repository is a pinned, public copy of the exact files the Rostrum apps download. Rostrum fetches each file at a fixed commit of this repository and checks its SHA-256 before use.

What Rostrum uses it for

Sound's transcripts and Compose's captions in any language, used when Parakeet is not sure.

Rostrum uses it for analysis only, never generation: it reads what is in a recording or a picture and makes no new sound, voice or image.

Files

File Bytes SHA-256
model.int8.onnx 1,031,628,252 f7b74c964039162423b83e3fa950ce24810c9a635d9ff8468b5f4d142b7c1e8c
tokens.txt 86,423 a7a044c52cb29cbe8b0dc1953e92cefd4ca16b0ed968177b6beab21f9a7d0b31

In Rostrum's models folder they go under omnilingual-1b-ctc/.

Source

What Where Commit / version
Exact files (unchanged copy) https://huggingface.co/csukuangfj/sherpa-onnx-omnilingual-asr-1600-languages-1B-ctc-int8-2025-11-12 17db76eab583b0b868ffb0df104ab879145087e5
Original model and code, Meta https://github.com/facebookresearch/omnilingual-asr 81f51e224ce9e74b02cc2a3eaf21b2d91d743455 (main when mirrored)

Authors

The Omnilingual ASR team, Meta (model and weights); Fangjun Kuang and the k2-fsa / Next-gen Kaldi team (int8 ONNX export).

Licence

"Omnilingual ASR code and models are released under the Apache 2.0" license (Meta). Meta's notice and the Apache-2.0 text are in LICENSE. The sherpa-onnx export code is Apache-2.0 (LICENSE-sherpa-onnx). Files redistributed unchanged.

Citation

The original authors ask that you cite:

@misc{omnilingualasrteam2025omnilingualasropensourcemultilingual,
      title={Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages},
      author={Omnilingual ASR team and Gil Keren and Artyom Kozhevnikov and Yen Meng and Christophe Ropers and Matthew Setzler and Skyler Wang and Ife Adebara and Michael Auli and Can Balioglu and Kevin Chan and Chierh Cheng and Joe Chuang and Caley Droof and Mark Duppenthaler and Paul-Ambroise Duquenne and Alexander Erben and Cynthia Gao and Gabriel Mejia Gonzalez and Kehan Lyu and Sagar Miglani and Vineel Pratap and Kaushik Ram Sadagopan and Safiyyah Saleem and Arina Turkatenko and Albert Ventayol-Boada and Zheng-Xin Yong and Yu-An Chung and Jean Maillard and Rashel Moritz and Alexandre Mourachko and Mary Williamson and Shireen Yates},
      year={2025},
      eprint={2511.09690},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2511.09690},
}
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including rostrumstudios/speech-languages

Paper for rostrumstudios/speech-languages