Automatic Speech Recognition
Transformers
Safetensors
fun_asr_nano
text-generation
speech-recognition
asr
end-to-end
multilingual
streaming
Instructions to use FunAudioLLM/Fun-ASR-Nano-2512-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FunAudioLLM/Fun-ASR-Nano-2512-hf with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="FunAudioLLM/Fun-ASR-Nano-2512-hf")# Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("FunAudioLLM/Fun-ASR-Nano-2512-hf", dtype="auto") - Notebooks
- Google Colab
- Kaggle
docs: clarify Nano language coverage
#1
by langgz - opened
Align the Transformers-compatible model card with the checkpoint's actual scope: Chinese, English, and Japanese, including 7 Chinese dialect groups and 26 regional accents. The separate Fun-ASR-MLT-Nano-2512 checkpoint provides 31-language recognition.
No model weights or inference code are changed.
Verified the server-side diff, YAML metadata, and PR-ref file hash. Merging the language-scope correction.
langgz changed pull request status to merged