From 4ba1011b42e041ee1d71448eefd7ef2e7bd61bb6 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 31 三月 2023 15:31:26 +0800
Subject: [PATCH] export

---
 funasr/runtime/python/libtorch/README.md |   15 ++++++++++++++-
 1 files changed, 14 insertions(+), 1 deletions(-)

diff --git a/funasr/runtime/python/libtorch/README.md b/funasr/runtime/python/libtorch/README.md
index 3904bc3..1912bbe 100644
--- a/funasr/runtime/python/libtorch/README.md
+++ b/funasr/runtime/python/libtorch/README.md
@@ -22,10 +22,19 @@
 
 
 2. Install the `funasr_torch`.
+    
+    install from pip
     ```shell
-    pip install funasr_torch -i https://pypi.Python.org/simple
+    pip install --upgrade funasr_torch -i https://pypi.Python.org/simple
     ```
+    or install from source code
 
+    ```shell
+    git clone https://github.com/alibaba/FunASR.git && cd FunASR
+    cd funasr/runtime/python/funasr_torch
+    python setup.py build
+    python setup.py install
+    ```
 
 3. Run the demo.
    - Model_dir: the model path, which contains `model.torchscripts`, `config.yaml`, `am.mvn`.
@@ -44,6 +53,10 @@
         print(result)
         ```
 
+## Performance benchmark
+
+Please ref to [benchmark](https://github.com/alibaba-damo-academy/FunASR/blob/main/funasr/runtime/python/benchmark_libtorch.md)
+
 ## Speed
 
 Environment锛欼ntel(R) Xeon(R) Platinum 8163 CPU @ 2.50GHz

--
Gitblit v1.9.1