Automatic Speech Recognition
Transformers
Safetensors
fun_asr_nano
text-generation
speech-recognition
asr
end-to-end
streaming
# Load model directly
from transformers import AutoModelForSeq2SeqLM
model = AutoModelForSeq2SeqLM.from_pretrained("FunAudioLLM/Fun-ASR-Nano-2512-hf", dtype="auto")Quick Links
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.
- Downloads last month
- 42
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="FunAudioLLM/Fun-ASR-Nano-2512-hf")