diff --git a/bindings/python/CHANGELOG.md b/bindings/python/CHANGELOG.md
index 80b7cd10..2e235daf 100644
--- a/bindings/python/CHANGELOG.md
+++ b/bindings/python/CHANGELOG.md
@@ -4,6 +4,16 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.8.1-rc1]
+
+### Fixed
+- [#333]: Fix deserialization of `AddedToken`, where the content was not restored properly
+
+### Changed
+- [#329]: Improved warning and behavior when we detect a fork
+- [#330]: BertNormalizer now keeps the same behavior than the original implementation when
+`strip_accents` is not specified.
+
 ## [0.8.0]
 
 ### Highlights of this release
@@ -209,6 +219,9 @@ delimiter (Works like `.split(delimiter)`)
 - Fix a bug with the IDs associated with added tokens.
 - Fix a bug that was causing crashes in Python 3.5
 
+[#333]: https://github.com/huggingface/tokenizers/pull/333
+[#330]: https://github.com/huggingface/tokenizers/pull/330
+[#329]: https://github.com/huggingface/tokenizers/pull/329
 [#311]: https://github.com/huggingface/tokenizers/pull/311
 [#309]: https://github.com/huggingface/tokenizers/pull/309
 [#289]: https://github.com/huggingface/tokenizers/pull/289
diff --git a/bindings/python/Cargo.lock b/bindings/python/Cargo.lock
index d06c2a15..e06c44e5 100644
--- a/bindings/python/Cargo.lock
+++ b/bindings/python/Cargo.lock
@@ -641,7 +641,7 @@ dependencies = [
 
 [[package]]
 name = "tokenizers-python"
-version = "0.8.0"
+version = "0.8.1-rc1"
 dependencies = [
  "libc 0.2.68 (registry+https://github.com/rust-lang/crates.io-index)",
  "pyo3 0.9.2 (registry+https://github.com/rust-lang/crates.io-index)",
diff --git a/bindings/python/Cargo.toml b/bindings/python/Cargo.toml
index d5d4cd32..93667444 100644
--- a/bindings/python/Cargo.toml
+++ b/bindings/python/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "tokenizers-python"
-version = "0.8.0"
+version = "0.8.1-rc1"
 authors = ["Anthony MOI <m.anthony.moi@gmail.com>"]
 edition = "2018"
 
diff --git a/bindings/python/setup.py b/bindings/python/setup.py
index 8109ff70..35eb3764 100644
--- a/bindings/python/setup.py
+++ b/bindings/python/setup.py
@@ -6,7 +6,7 @@ extras["testing"] = ["pytest"]
 
 setup(
     name="tokenizers",
-    version="0.8.0",
+    version="0.8.1.rc1",
     description="Fast and Customizable Tokenizers",
     long_description=open("README.md", "r", encoding="utf-8").read(),
     long_description_content_type="text/markdown",
diff --git a/bindings/python/tokenizers/__init__.py b/bindings/python/tokenizers/__init__.py
index 658e8c12..f1261aa1 100644
--- a/bindings/python/tokenizers/__init__.py
+++ b/bindings/python/tokenizers/__init__.py
@@ -1,4 +1,4 @@
-__version__ = "0.8.0"
+__version__ = "0.8.1.rc1"
 
 from typing import Tuple, Union, Tuple, List
 
diff --git a/tokenizers/CHANGELOG.md b/tokenizers/CHANGELOG.md
index 5d8e2de9..a1c847c1 100644
--- a/tokenizers/CHANGELOG.md
+++ b/tokenizers/CHANGELOG.md
@@ -34,6 +34,8 @@ implementation from GPT-2
 - [#309]: Improved the management of the additional vocabulary. This introduces an option
 `normalized`, controlling whether a token should be extracted from the normalized version of the
 input text.
+- [#330]: BertNormalizer now keeps the same behavior than the original implementation when
+`strip_accents` is not specified.
 
 ### Added
 - [#236]: RobertaProcessing is now also taking care of trimming offsets, and works just as ByteLevel
@@ -119,6 +121,7 @@ advised, but that's not the question)
 split up in multiple bytes
 - [#174]: The `LongestFirst` truncation strategy had a bug
 
+[#330]: https://github.com/huggingface/tokenizers/pull/330
 [#311]: https://github.com/huggingface/tokenizers/pull/311
 [#309]: https://github.com/huggingface/tokenizers/pull/309
 [#298]: https://github.com/huggingface/tokenizers/pull/298