From 46357e96f4359c4b552b8e08136e9239da586d32 Mon Sep 17 00:00:00 2001
From: lyblsgo <lyblsgo@163.com>
Date: 星期一, 08 五月 2023 14:33:23 +0800
Subject: [PATCH] update onnxruntime readme
---
funasr/runtime/onnxruntime/readme.md | 22 ++++++++++++++++++++++
1 files changed, 22 insertions(+), 0 deletions(-)
diff --git a/funasr/runtime/onnxruntime/readme.md b/funasr/runtime/onnxruntime/readme.md
index f3dc3b6..5b42c30 100644
--- a/funasr/runtime/onnxruntime/readme.md
+++ b/funasr/runtime/onnxruntime/readme.md
@@ -124,6 +124,28 @@
--model-dir ./asrmodel/punc_ct-transformer_zh-cn-common-vocab272727-pytorch \
--txt-path ./punc_example.txt
```
+### funasr-onnx-offline-rtf
+```shell
+./funasr-onnx-offline-rtf --thread-num <int32_t> --wav-scp <string>
+ [--quantize <string>] --model-dir <string>
+ [--] [--version] [-h]
+Where:
+ --thread-num <int32_t>
+ (required) multi-thread num for rtf
+ --model-dir <string>
+ (required) the model path, which contains model.onnx, config.yaml, am.mvn
+ --quantize <string>
+ false (Default), load the model of model.onnx in model_dir. If set true, load the model of model_quant.onnx in model_dir
+ --wav-scp <string>
+ (required) wave scp path
+
+For example:
+./funasr-onnx-offline-rtf \
+ --model-dir ./asrmodel/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch \
+ --quantize true \
+ --wav-scp ./aishell1_test.scp \
+ --thread-num 32
+```
## Acknowledge
1. This project is maintained by [FunASR community](https://github.com/alibaba-damo-academy/FunASR).
--
Gitblit v1.9.1