Zhifu Gao

Add README with pipeline_tag: automatic-speech-recognition

9436970 2 days ago

919 Bytes

language:
  - zh
  - en
  - ja
  - ko
  - yue
  - vi
  - id
  - th
  - ms
  - tl
  - ar
  - hi
  - multilingual
license: apache-2.0
library_name: transformers
pipeline_tag: automatic-speech-recognition
tags:
  - speech-recognition
  - asr
  - end-to-end
  - multilingual
  - streaming

Fun-ASR-Nano (HuggingFace Transformers)

This is the HuggingFace Transformers-compatible version of Fun-ASR-Nano-2512.

Fun-ASR-Nano is an end-to-end speech recognition model by FunAudioLLM, trained on tens of millions of hours of real speech data. It supports multilingual speech recognition covering Chinese (with dialects), English, Japanese, Korean, and many more languages.

For full documentation, benchmarks, and usage instructions, please refer to the main model card.