diff --git a/.github/workflows/python-publish.yml b/.github/workflows/python-publish.yml
new file mode 100644
index 000000000..116c85937
--- /dev/null
+++ b/.github/workflows/python-publish.yml
@@ -0,0 +1,37 @@
+name: Release
+
+on:
+  push:
+    branches:
+    - main
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - uses: actions-ecosystem/action-regex-match@v2
+      id: regex-match
+      with:
+        text: ${{ github.event.head_commit.message }}
+        regex: '^Release ([^ ]+)'
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.8'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install setuptools wheel twine
+    - name: Release
+      if: ${{ steps.regex-match.outputs.match != '' }}
+      uses: softprops/action-gh-release@v1
+      with:
+        tag_name: v${{ steps.regex-match.outputs.group1 }}
+    - name: Build and publish
+      if: ${{ steps.regex-match.outputs.match != '' }}
+      env:
+        TWINE_USERNAME: __token__
+        TWINE_PASSWORD: ${{ secrets.PYPI_API_TOKEN }}
+      run: |
+        python setup.py sdist
+        twine upload dist/*
diff --git a/MANIFEST.in b/MANIFEST.in
index 838aa2d9c..f091bded7 100644
--- a/MANIFEST.in
+++ b/MANIFEST.in
@@ -1,3 +1,6 @@
+include requirements.txt
+include README.md
+include LICENSE
 include whisper/assets/*
 include whisper/assets/gpt2/*
 include whisper/assets/multilingual/*
diff --git a/README.md b/README.md
index 281561b42..9d39f8202 100644
--- a/README.md
+++ b/README.md
@@ -2,7 +2,7 @@
 
 [[Blog]](https://openai.com/blog/whisper)
 [[Paper]](https://arxiv.org/abs/2212.04356)
-[[Model card]](model-card.md)
+[[Model card]](https://github.com/openai/whisper/blob/main/model-card.md)
 [[Colab example]](https://colab.research.google.com/github/openai/whisper/blob/master/notebooks/LibriSpeech.ipynb)
 
 Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification.
@@ -10,14 +10,14 @@ Whisper is a general-purpose speech recognition model. It is trained on a large
 
 ## Approach
 
-![Approach](approach.png)
+![Approach](https://raw.githubusercontent.com/openai/whisper/main/approach.png)
 
 A Transformer sequence-to-sequence model is trained on various speech processing tasks, including multilingual speech recognition, speech translation, spoken language identification, and voice activity detection. All of these tasks are jointly represented as a sequence of tokens to be predicted by the decoder, allowing for a single model to replace many different stages of a traditional speech processing pipeline. The multitask training format uses a set of special tokens that serve as task specifiers or classification targets.
 
 
 ## Setup
 
-We used Python 3.9.9 and [PyTorch](https://pytorch.org/) 1.10.1 to train and test our models, but the codebase is expected to be compatible with Python 3.7 or later and recent PyTorch versions. The codebase also depends on a few Python packages, most notably [HuggingFace Transformers](https://huggingface.co/docs/transformers/index) for their fast tokenizer implementation and [ffmpeg-python](https://github.com/kkroening/ffmpeg-python) for reading audio files. The following command will pull and install the latest commit from this repository, along with its Python dependencies 
+We used Python 3.9.9 and [PyTorch](https://pytorch.org/) 1.10.1 to train and test our models, but the codebase is expected to be compatible with Python 3.7 or later and recent PyTorch versions. The codebase also depends on a few Python packages, most notably [HuggingFace Transformers](https://huggingface.co/docs/transformers/index) for their fast tokenizer implementation and [ffmpeg-python](https://github.com/kkroening/ffmpeg-python) for reading audio files. The following command will pull and install the latest commit from this repository, along with its Python dependencies:
 
     pip install git+https://github.com/openai/whisper.git 
 
@@ -68,7 +68,7 @@ For English-only applications, the `.en` models tend to perform better, especial
 
 Whisper's performance varies widely depending on the language. The figure below shows a WER (Word Error Rate) breakdown by languages of Fleurs dataset, using the `large-v2` model. More WER and BLEU scores corresponding to the other models and datasets can be found in Appendix D in [the paper](https://arxiv.org/abs/2212.04356). The smaller is better.
 
-![WER breakdown by language](language-breakdown.svg)
+![WER breakdown by language](https://raw.githubusercontent.com/openai/whisper/main/language-breakdown.svg)
 
 
 
@@ -90,7 +90,7 @@ Run the following to view all available options:
 
     whisper --help
 
-See [tokenizer.py](whisper/tokenizer.py) for the list of all available languages.
+See [tokenizer.py](https://github.com/openai/whisper/blob/main/whisper/tokenizer.py) for the list of all available languages.
 
 
 ## Python usage
@@ -140,4 +140,4 @@ Please use the [🙌 Show and tell](https://github.com/openai/whisper/discussion
 
 ## License
 
-The code and the model weights of Whisper are released under the MIT License. See [LICENSE](LICENSE) for further details.
+The code and the model weights of Whisper are released under the MIT License. See [LICENSE](https://github.com/openai/whisper/blob/main/LICENSE) for further details.
diff --git a/setup.py b/setup.py
index 13f341ea6..0e822ab9e 100644
--- a/setup.py
+++ b/setup.py
@@ -3,11 +3,19 @@
 import pkg_resources
 from setuptools import setup, find_packages
 
+
+def read_version(fname="whisper/version.py"):
+    exec(compile(open(fname, encoding="utf-8").read(), fname, "exec"))
+    return locals()["__version__"]
+
+
 setup(
-    name="whisper",
+    name="openai-whisper",
     py_modules=["whisper"],
-    version="1.0",
+    version=read_version(),
     description="Robust Speech Recognition via Large-Scale Weak Supervision",
+    long_description=open("README.md", encoding="utf-8").read(),
+    long_description_content_type="text/markdown",
     readme="README.md",
     python_requires=">=3.7",
     author="OpenAI",
@@ -20,9 +28,9 @@
             open(os.path.join(os.path.dirname(__file__), "requirements.txt"))
         )
     ],
-    entry_points = {
-        'console_scripts': ['whisper=whisper.transcribe:cli'],
+    entry_points={
+        "console_scripts": ["whisper=whisper.transcribe:cli"],
     },
     include_package_data=True,
-    extras_require={'dev': ['pytest']},
+    extras_require={"dev": ["pytest"]},
 )
diff --git a/whisper/__init__.py b/whisper/__init__.py
index f80fe721b..2a1fb4ec6 100644
--- a/whisper/__init__.py
+++ b/whisper/__init__.py
@@ -12,6 +12,7 @@
 from .decoding import DecodingOptions, DecodingResult, decode, detect_language
 from .model import Whisper, ModelDimensions
 from .transcribe import transcribe
+from .version import __version__
 
 
 _MODELS = {
diff --git a/whisper/version.py b/whisper/version.py
new file mode 100644
index 000000000..8c605f4d5
--- /dev/null
+++ b/whisper/version.py
@@ -0,0 +1 @@
+__version__ = "20230117"