From 1dbb526150b4d08400c97b72c5e79c9af0c3c6da Mon Sep 17 00:00:00 2001
From: DoodleBears <yangmufeng233@gmail.com>
Date: Mon, 1 Jul 2024 04:03:03 +0900
Subject: [PATCH] doc(README): add Google Colab link

---
 README.md             | 17 +++++++++++------
 setup.py              |  1 +
 split-lang-demo.ipynb |  3 ++-
 3 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/README.md b/README.md
index 6ea8d97..2e9decd 100644
--- a/README.md
+++ b/README.md
@@ -4,6 +4,9 @@
 [![Downloads](https://static.pepy.tech/badge/split-lang)](https://pepy.tech/project/split-lang)
 [![Downloads](https://static.pepy.tech/badge/split-lang/month)](https://pepy.tech/project/split-lang)
 
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/DoodleBears/split-lang/blob/main/split-lang-demo.ipynb)
+
+
 [![Open Source Love](https://badges.frapsoft.com/os/mit/mit.svg?v=102)](https://github.com/ellerbrock/open-source-badge/)
 
 [![wakatime](https://wakatime.com/badge/user/5728d95a-5cfb-4acb-b600-e34c2fc231b6/project/e06e0a00-9ba1-453d-8c62-a0b2604aaaad.svg)](https://wakatime.com/badge/user/5728d95a-5cfb-4acb-b600-e34c2fc231b6/project/e06e0a00-9ba1-453d-8c62-a0b2604aaaad)
@@ -12,7 +15,7 @@ Splitting sentences by concatenating over-split substrings based on their langua
 
 powered by [`wtpsplit`](https://github.com/segment-any-text/wtpsplit) and [`fast-langdetect`](https://github.com/LlmKira/fast-langdetect) and [`langdetect`](https://github.com/Mimino666/langdetect)
 
-## Idea
+## 1.1. Idea
 
 **Stage 1**: rule-based split using punctuation
 - `hello, how are you` -> `hello` | `,` | `how are you`
@@ -39,15 +42,15 @@ Vielen Dank merci beaucoup for your help.
 ```
 
 - [1. `split-lang`](#1-split-lang)
-  - [Idea](#idea)
+  - [1.1. Idea](#11-idea)
 - [2. Motivation](#2-motivation)
 - [3. Usage](#3-usage)
   - [3.1. Installation](#31-installation)
   - [3.2. Basic](#32-basic)
     - [3.2.1. `split_by_lang`](#321-split_by_lang)
   - [3.3. Advanced](#33-advanced)
-    - [`threshold`](#threshold)
-    - [3.3.1. usage of `lang_map` (for better result)](#331-usage-of-lang_map-for-better-result)
+    - [3.3.1. `threshold`](#331-threshold)
+    - [3.3.2. usage of `lang_map` (for better result)](#332-usage-of-lang_map-for-better-result)
 
 
 # 3. Usage
@@ -65,6 +68,8 @@ pip install split-lang
 ## 3.2. Basic
 ### 3.2.1. `split_by_lang`
 
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/DoodleBears/split-lang/blob/main/split-lang-demo.ipynb)
+
 ```python
 from split_lang import split_by_lang
 
@@ -92,7 +97,7 @@ for text in texts:
 
 ## 3.3. Advanced
 
-### `threshold`
+### 3.3.1. `threshold`
 
 the threshold used in `wtpsplit`, default to 1e-4, the smaller the more substring you will get in `wtpsplit` stage
 
@@ -100,7 +105,7 @@ the threshold used in `wtpsplit`, default to 1e-4, the smaller the more substrin
 > Check GitHub Repo `tests/split_acc.py` to find best threshold for your use case
 
 
-### 3.3.1. usage of `lang_map` (for better result)
+### 3.3.2. usage of `lang_map` (for better result)
 
 > [!IMPORTANT]
 > Add lang code for your usecase if other languages are needed
diff --git a/setup.py b/setup.py
index cd6cd2a..8fcfc60 100644
--- a/setup.py
+++ b/setup.py
@@ -20,6 +20,7 @@ def read(*relpath):
     url="https://github.com/DoodleBears/langsplit",
     author="DoodleBear",
     author_email="yangmufeng233@gmail.com",
+    license="MIT",
     packages=find_packages(),
     install_requires=[
         "langdetect",
diff --git a/split-lang-demo.ipynb b/split-lang-demo.ipynb
index 62a4b64..0523b3c 100644
--- a/split-lang-demo.ipynb
+++ b/split-lang-demo.ipynb
@@ -6,7 +6,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install split-lang --upgrade"
+    "%pip install split-lang --upgrade\n",
+    "%pip install numpy==1.26.0"
    ]
   },
   {