Update

Author: wenbinf

README.md

@@ -1,28 +1,53 @@
 # NotebookLM Detector
 
-This is a simple tool to detect if an audio file is generated by NotebookLM.
+A simple tool to detect whether an audio file was generated by [NotebookLM](https://notebooklm.google/).
 
-## Detect
+At [Listen Notes](https://www.listennotes.com/), we've encountered a growing number of spammers submitting fake, 
+NotebookLM-generated podcasts to our platform. 
 
-Install dependencies first:
+We hoped the NotebookLM team would provide a tool to help detect NotebookLM-generated audio. 
+However, after a week of back-and-forth emails, we lost patience.
+
+It's now Friday (Oct 4, 2024), and since we won't hear back from the NotebookLM team until next week,
+we decided to put together this simple script. Luckily, it seems to work!
+
+
+## Detection
+
+### Install Dependencies
 
 ```shell
 $ pip install -r requirements.txt
 ```
 
-Run the script to detect:
+### Run the Detection Script
+
+To detect whether an audio file is AI-generated or human-produced, run the following command:
 ```shell
 $ python notebooklm_detector.py --action predict --file_path [filename].mp3
 ```
 
-## Train
+You’ll see output like this:
+```shell
+$ The audio is: AI Generated
+```
+or
+```shell
+$ The audio is: Human
+```
+
+## Training the Model
+
+You can train the model and regenerate `model.pkl` by following these steps:
+
+### Step 1: Organize the Dataset
 
-You can train and regenerate model.pkl:
+* Place NotebookLM-generated audio files (mp3, wav, or mp4) in the datasets/ai/ folder.
+* Place human-produced audio files in the datasets/human/ folder.
 
-Step 1: Put NotebookLM-generated audio files (mp3, wav, or mp4) in datasets/ai/ folder. 
-And put human-produced audio files in datasets/human/ folder. 
+### Step 2: Run the Training Script
 
-Step 2: Run the script to train:
+To train the model, run:
 ```shell
 $ python notebooklm_detector.py --action train --dataset_path datasets
 ```