Project AURIONAI Use-Cases Research & Innovation
Alibaba (Qwen)
speech recognition

Fun-ASR-Nano (Fun-ASR-Nano-2512)

Alibaba FunAudioLLM ASR model. Licence resolved to Apache-2.0: no licence file in the repos; model card and publisher GitHub state Apache-2.0.

Alibaba (Qwen)Alibaba (Qwen)China
Bar chart comparing Fun-ASR-Nano speech recognition accuracy with other models across test sets.
Levelmodel
Classspeech recognition
Parameters800M
Contextnot in the notes
Released15 Dec 2025
Opennessopen weights permissive
Runs onsingle datacentre GPU
Statusactive

R&D Topics

Massively multilingual speech recognitionproduced byAudio language models for speech understandingproduced by

Runtimes

llama.cppggml-org, mit

Identity

Developer
Alibaba (Qwen)
Family
not in the notes
Released
15 Dec 2025 sourcesregistry date
Weights published
–
Record checked
10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
other
Total parameters
800M sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
audio
Output
text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
open weights permissive
Licence
Apache License 2.0 sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
single datacentre GPU
Footprint
not in the notes
Runtimes
llama.cpp
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
zh/en/ja + Chinese dialects
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Lineage

The notes record no lineage for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. GitHub - modelscope/FunASR: Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diariza github.com/modelscope/FunASR https://github.com/modelscope/FunASR
  2. FunAudioLLM/Fun-ASR-Nano-2512 , Hugging Face huggingface.co https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512
  3. GitHub - QwenAudio/Fun-ASR: Fun-ASR speech recognition models, with native Hugging Face Transformers support for Fun-ASR-Nano and separate F github.com https://github.com/FunAudioLLM/Fun-ASR
  4. GitHub - modelscope/FunASR: Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diariza github.com/modelscope/FunASR https://github.com/modelscope/FunASR
  5. huggingface.co/api/models/FunAudioLLM/Fun-ASR-Nano-2512 https://huggingface.co/api/models/FunAudioLLM/Fun-ASR-Nano-2512

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Fun-ASR-Nano (Fun-ASR-Nano-2512)", https://aurion.semai.id/models/alibaba-fun-asr-nano/, records of October 2026.