diff --git a/docs/source/decoding-with-langugage-models/LODR.rst b/docs/source/decoding-with-langugage-models/LODR.rst
new file mode 100644
index 000000000..6db2366af
--- /dev/null
+++ b/docs/source/decoding-with-langugage-models/LODR.rst
@@ -0,0 +1,4 @@
+.. _LODR:
+
+LODR for RNN Transducer
+=======================
\ No newline at end of file
diff --git a/docs/source/decoding-with-langugage-models/index.rst b/docs/source/decoding-with-langugage-models/index.rst
new file mode 100644
index 000000000..97dc98b01
--- /dev/null
+++ b/docs/source/decoding-with-langugage-models/index.rst
@@ -0,0 +1,11 @@
+Decoding with language models
+=============================
+
+This section describes how to use external langugage models 
+during decoding to improve the WER of transducer models.
+
+.. toctree::
+   :maxdepth: 2
+
+   shallow-fusion
+   LODR
diff --git a/docs/source/decoding-with-langugage-models/shallow-fusion.rst b/docs/source/decoding-with-langugage-models/shallow-fusion.rst
new file mode 100644
index 000000000..3ee8a91ac
--- /dev/null
+++ b/docs/source/decoding-with-langugage-models/shallow-fusion.rst
@@ -0,0 +1,152 @@
+.. _shallow_fusion:
+
+Shallow fusion for RNN Transducer
+=================================
+
+In real-life scenario, there is often a mismatch between the training corpus and the target corpus space. 
+Therefore, we often use an external language model (LM) to improve the accuracy of the ASR model
+on the target space. Even if the training and testing domain are similar, using external langugage model
+can still help the ASR model if the training corpus is not that large. 
+This tutorial shows you how to perform ``shallow fusion`` with an external LM
+to improve the word-error-rate of a RNN Transducer model.
+
+.. note::
+
+    This tutorial is based on the recipe 
+    `pruned_transducer_stateless7_streaming <https://github.com/k2-fsa/icefall/tree/master/egs/librispeech/ASR/pruned_transducer_stateless7_streaming>`_,
+    which is a streaming transducer model trained on `LibriSpeech`_. 
+    However, you can easily apply shallow fusion to other recipes.
+    If you encounter any problems, please open an issue here `icefall <https://github.com/k2-fsa/icefall/issues>`_.
+
+.. note::
+
+    For simplicity, the training and testing corpus in this tutorial is the same (`LibriSpeech`_). However, you can change the testing set
+    to any other domains (e.g GigaSpeech) and use an external LM trained on that domain.
+
+.. HINT::
+
+  We recommend you to use a GPU for decoding.
+
+For illustration purpose, we will use a pre-trained ASR model from this `link <https://huggingface.co/Zengwei/icefall-asr-librispeech-pruned-transducer-stateless7-streaming-2022-12-29>`_.
+If you want to train your model from scratch, please have a look at :ref:`non_streaming_librispeech_pruned_transducer_stateless`.
+
+As the initial step, let's download the pre-trained model.
+
+.. code-block:: bash
+
+    $ git lfs install
+    $ git clone https://huggingface.co/Zengwei/icefall-asr-librispeech-pruned-transducer-stateless7-streaming-2022-12-29
+    $ pushd icefall-asr-librispeech-pruned-transducer-stateless7-streaming-2022-12-29/exp
+    $ ln -s pretrained.pt epoch-99.pt # create a symbolic link so that the checkpoint can be loaded
+
+To test the model, let's have a look at the decoding results without using LM. This can be done via the following command:
+
+.. code-block:: bash
+
+    $ exp_dir=./icefall-asr-librispeech-pruned-transducer-stateless7-streaming-2022-12-29/exp/
+    $ ./pruned_transducer_stateless7_streaming/decode.py \
+        --epoch 30 \
+        --avg 9 \
+        --exp-dir $exp_dir \
+        --max-duration 600 \
+        --decode-chunk-len 32 \
+        --decoding-method modified_beam_search
+
+The following WERs are achieved on test-clean and test-other:
+
+.. code-block:: bash
+
+    $ For test-clean, WER of different settings are:
+    $ beam_size_4	3.11	best for test-clean
+    $ For test-other, WER of different settings are:
+    $ beam_size_4	7.93	best for test-other
+
+These are already good numbers! But we can further improve it by using shallow fusion with external LM.
+Training a language model usually takes a long time, we can download a pre-trained LM from this `link <https://huggingface.co/ezerhouni/icefall-librispeech-rnn-lm>`_.
+
+.. code-block:: bash
+
+    $ git lfs install
+    $ git clone https://huggingface.co/ezerhouni/icefall-librispeech-rnn-lm
+    $ pushd icefall-librispeech-rnn-lm/exp
+    $ ln -s pretrained.pt epoch-99.pt # create a symbolic link so that the checkpoint can be loaded
+    $ popd
+
+.. note::
+
+    This is an RNN LM trained on the LibriSpeech text corpus. So it might not be ideal for other corpus.
+    You may also train a RNN LM from scratch. Please refer to this `script <https://github.com/k2-fsa/icefall/blob/master/icefall/rnn_lm/train.py>`_
+    for training a RNN LM and this `script <https://github.com/k2-fsa/icefall/blob/master/icefall/transformer_lm/train.py>`_ to train a transformer LM.
+
+To use shallow fusion for decoding, we can execute the following command:
+
+.. code-block:: bash
+    
+    $ exp_dir=./icefall-asr-librispeech-pruned-transducer-stateless7-streaming-2022-12-29/exp
+    $ lm_dir=./icefall-librispeech-rnn-lm/exp
+    $ ./pruned_transducer_stateless7_streaming/decode.py \
+        --epoch 99 \
+        --avg 1 \
+        --use-averaged-model False \
+        --beam-size 4 \
+        --exp-dir $exp_dir \
+        --max-duration 600 \
+        --decode-chunk-len 32 \
+        --decoding-method modified_beam_search_lm_shallow_fusion \
+        --bpe-model ./icefall-asr-librispeech-pruned-transducer-stateless7-streaming-2022-12-29/data/lang_bpe_500/bpe.model
+        --use-shallow-fusion 1 \
+        --lm-type rnn \
+        --lm-exp-dir $lm_dir \
+        --lm-epoch 99 \
+        --lm-scale 0.29 \
+        --lm-avg 1 \
+        --rnn-lm-embedding-dim 2048 \
+        --rnn-lm-hidden-dim 2048 \
+        --rnn-lm-num-layers 3 \
+        --lm-vocab-size 500
+
+Note that we set ``--decoding-method modified_beam_search_lm_shallow_fusion`` and ``--use-shallow-fusion True``
+to use shallow fusion. ``--lm-type`` specifies the type of neural LM we are going to use, you can either choose
+between ``rnn`` or ``transformer``. The following three arguments are associated with the rnn:
+
+- ``--rnn-lm-embedding-dim``
+    The embedding dimension of the RNN LM
+
+- ``--rnn-lm-hidden-dim``
+    The hidden dimension of the RNN LM
+
+- ``--rnn-lm-num-layers``
+    The number of RNN layers in the RNN LM.
+
+
+The decoding result obtained with the above command are shown below.
+
+.. code-block:: bash
+
+    $ For test-clean, WER of different settings are:
+    $ beam_size_4	2.77	best for test-clean
+    $ For test-other, WER of different settings are:
+    $ beam_size_4	7.08	best for test-other
+
+The improvement of shallow fusion is very obvious! The relative WER reduction on test-other is around 10.5%. 
+A few parameters can be tuned to further boost the performance of shallow fusion:
+
+- ``--lm-scale`` 
+
+    Controls the scale of the LM. If too small, the external language model may not be fully utilized; if too large, 
+    the LM score may dominant during decoding, leading to bad WER. A typical value of this is around 0.3.
+
+- ``--beam-size`` 
+    
+    The number of active paths in the search beam. It controls the trade-off between decoding efficiency and accuracy.
+
+
+
+
+
+
+
+
+
+
+ 
diff --git a/docs/source/index.rst b/docs/source/index.rst
index 8d76eb68b..a7d365a15 100644
--- a/docs/source/index.rst
+++ b/docs/source/index.rst
@@ -34,3 +34,8 @@ speech recognition recipes using `k2 <https://github.com/k2-fsa/k2>`_.
 
    contributing/index
    huggingface/index
+
+.. toctree::
+   :maxdepth: 2
+   
+   decoding-with-langugage-models/index
\ No newline at end of file