Merge branch 'main' of https://github.com/VladBastina/MeetingUnderstanding into main

README.md

@@ -0,0 +1,49 @@
+# Video Meeting Understanding
+
+This project uses gemini tu make a report about a video of a meeting using the video itself aswell as the transcript of the meeting.
+
+## Requirements
+Python 3.12
+
+## How to setup
+1. Create an environment and install dependecies
+   
+   ```bash
+   conda create -n meetUnder python=3.12
+   conda activate meetUnder
+   pip install -r requirements.txt
+   ```
+
+2. Setup secrets in for streamlit
+
+   2.1 Create a new file in the .streamlit folder and name it secrets.toml. You will insert here the following keys
+
+   ```bash
+   GOOGLE_API_KEY = 'your_key_here'
+   ```
+
+   2.2 Create a new project in google cloud platform and activate the google cloud speech-to-text api and then create a new credentials for a service account and download the json key. Then copy paste the info in the json and put everything in one line and replace the : with =
+
+   ```bash
+   GOOGLE_APPLICATION_CREDENTIALS = { #json info here }
+   ```
+
+## How to run
+
+```bash
+streamlit run app.py
+```
+
+## How it works
+
+**app.py** is the main point that controls the ui in streamlit
+
+**cloud_speech.py** makes the transcription of the sound file of the meeting
+
+**vision_api_call.py** The name is wron for what it does. This is the file that takes the transcription and the video itself and gives them to gemini api that makes the report.
+
+## Where to find it
+
+Path on **rtx** : /home/vladp/Projects/meetingUnderstanding/
+
+Env : meetUnder