Skip to content

Add Fun-ASR-Nano — speech encoder + LLM transformer model #7

Open
Open
Add Fun-ASR-Nano — speech encoder + LLM transformer model#7
Assignees
LauraGPT

Description

@LauraGPT
LauraGPT
opened on Jun 1, 2026

Note

License and capability clarification (2026-07-14): FunASR is a toolkit, not a single checkpoint. The FunASR and SenseVoice repository source code is MIT; model weights follow each model card. SenseVoiceSmall supports Chinese, Cantonese, English, Japanese, and Korean, and its weights use the linked FunASR Model Open Source License Agreement. Fun-ASR-Nano-2512 is Apache-2.0. Language coverage, punctuation, and performance depend on the selected model and runtime configuration.

Hi! Great curated list of transformer models.

Would you consider adding Fun-ASR-Nano?

Fun-ASR-Nano

  • Architecture: Audio encoder + Qwen2.5-0.5B LLM (transformer-based)
  • Task: End-to-end speech recognition
  • Notable: First speech model being integrated into HuggingFace Transformers natively (PR #46180)
  • Stars: 1.2K
  • License: Apache 2.0
  • HuggingFace: https://huggingface.co/FunAudioLLM/Fun-ASR-Nano

Also relevant:

Activity

  1. LauraGPT commented on Jun 12, 2026

    @LauraGPT
    LauraGPT
    on Jun 12, 2026
    Author

    Hi! FunASR has grown to 17.8K+ stars. Still interested in this integration? Happy to help! 🙏

  2. abacaj
    assigned
    LauraGPT
    on Jun 16, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

Labels

No labels
No labels

Projects

No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions