Beta

Explore
Marketplace
Neural Labs
Chat
Wallet
Docs

Beta

Explore Marketplace Neural Labs Wallet Docs

Build

Manage

My assets Manage wallet Organization

Community

Discord X (Twitter)Telegram

Docs Privacy Policy Terms and Conditions

Proud member of

Proud member of

Docs Cookie Policy

Privacy Policy Terms and Conditions

© 2026 AlphaNeural AI. All rights reserved.

sherpa-onnx-ort-paraformer-en-2024-03-09 – AI Model by imedemi | AlphaNeural AI

You can deploy this model and start earning money today!

imedemi/
sherpa-onnx-ort-paraformer-en-2024-03-09

like

0

Views

No views yet

sherpa-onnx-ort-paraformer-en-2024-03-09

ORT-converted version of csukuangfj/sherpa-onnx-paraformer-en-2024-03-09 for faster model loading.

Model details

Architecture: Paraformer (Alibaba, non-autoregressive)
Format: ORT (pre-optimized ONNX Runtime format)
Quantization: int8
Files: model (219 MB), tokens.txt

Benchmark (Boox Palma 2 Pro, Snapdragon 690)

On unseen evaluation data (Earnings-22 + TED-LIUM 3):

WER: 13.8% (8.0% Earnings-22, 19.7% TED-LIUM)
RTF: 0.08 (12x faster than real-time)
Native memory: +503 MB

Conversion

bash

pip install onnxruntime onnx
python -m onnxruntime.tools.convert_onnx_models_to_ort --optimization_style=Fixed .