diff --git a/docs/README.md b/docs/README.md
new file mode 100644
index 000000000..3abb38f8b
--- /dev/null
+++ b/docs/README.md
@@ -0,0 +1,24 @@
+
+## Usage
+
+```bash
+cd /path/to/icefall/docs
+pip install -r requirements.txt
+make clean
+make html
+cd build/html
+python3 -m http.server 8000
+```
+
+It prints:
+
+```
+Serving HTTP on 0.0.0.0 port 8000 (http://0.0.0.0:8000/) ...
+```
+
+Open your browser and go to <http://0.0.0.0:8000/> to view the generated
+documentation.
+
+Done!
+
+**Hint**: You can change the port number when starting the server.
diff --git a/docs/source/recipes/Streaming-ASR/librispeech/lstm_pruned_stateless_transducer.rst b/docs/source/recipes/Streaming-ASR/librispeech/lstm_pruned_stateless_transducer.rst
index 643855cc2..d09421eb5 100644
--- a/docs/source/recipes/Streaming-ASR/librispeech/lstm_pruned_stateless_transducer.rst
+++ b/docs/source/recipes/Streaming-ASR/librispeech/lstm_pruned_stateless_transducer.rst
@@ -531,16 +531,36 @@ First, let us install a modified version of ``ncnn``:
   git clone https://github.com/csukuangfj/ncnn
   cd ncnn
   git submodule update --recursive --init
-  python3 setup.py bdist_wheel
-  ls -lh dist/
-  pip install ./dist/*.whl
+
+  # Note: We don't use "python setup.py install" or "pip install ." here
+
+  mkdir -p build-wheel
+  cd build-wheel
+
+  cmake \
+    -DCMAKE_BUILD_TYPE=Release \
+    -DNCNN_PYTHON=ON \
+    -DNCNN_BUILD_BENCHMARK=OFF \
+    -DNCNN_BUILD_EXAMPLES=OFF \
+    -DNCNN_BUILD_TOOLS=OFF \
+    ..
+
+  make -j4
+
+  cd ..
+
+  # Note: $PWD here is /path/to/ncnn
+
+  export PYTHONPATH=$PWD/python:$PYTHONPATH
+  export PATH=$PWD/tools/pnnx/build/src:$PATH
+  export PATH=$PWD/build/tools/quantize:$PATH
 
   # now build pnnx
   cd tools/pnnx
   mkdir build
   cd build
+  cmake ..
   make -j4
-  export PATH=$PWD/src:$PATH
 
   ./src/pnnx
 
@@ -549,6 +569,9 @@ First, let us install a modified version of ``ncnn``:
    We assume that you have added the path to the binary ``pnnx`` to the
    environment variable ``PATH``.
 
+   We also assume that you have added ``build/tools/quantize`` to the environment
+   variable ``PATH`` so that you are able to use ``ncnn2int8`` later.
+
 Second, let us export the model using ``torch.jit.trace()`` that is suitable
 for ``pnnx``: