# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("moeru-ai/sherpa-onnx-streaming-zipformer-ar_en_id_ja_ru_th_vi_zh-2025-02-10", device_map="auto")Quick Links
Model Description
A faster and better encoder for automatic speech recognition
Intended Uses
Low latency speech recognition tasks, especially in streaming scenarios.
Limitations
Single language, no LLM corrector
Model Description
A faster and better encoder for automatic speech recognition
Intended Uses
Low latency speech recognition tasks, especially in streaming scenarios.
Limitations
Single language, no LLM corrector
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="moeru-ai/sherpa-onnx-streaming-zipformer-ar_en_id_ja_ru_th_vi_zh-2025-02-10")