Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/neonwatty/bleep_that_sht
Make someone sound naughty - bleep out words of your choice leveraging Whisper transcription
https://github.com/neonwatty/bleep_that_sht
ai demo-app generative-ai machine-learning transcribe transcription whisper
Last synced: 3 months ago
JSON representation
Make someone sound naughty - bleep out words of your choice leveraging Whisper transcription
- Host: GitHub
- URL: https://github.com/neonwatty/bleep_that_sht
- Owner: neonwatty
- License: apache-2.0
- Created: 2024-06-08T20:57:15.000Z (8 months ago)
- Default Branch: main
- Last Pushed: 2024-07-23T18:13:18.000Z (6 months ago)
- Last Synced: 2024-09-27T06:22:16.467Z (4 months ago)
- Topics: ai, demo-app, generative-ai, machine-learning, transcribe, transcription, whisper
- Language: Jupyter Notebook
- Homepage: https://bleepthatsht.xyz/
- Size: 17.6 MB
- Stars: 15
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
[](https://github.com/neonwatty/bleep_that_sht/actions/workflows/python-app.yml/python-app.yml) 
# bleep that sh*t
Make anyone sound naughty / funny with Python.
Bleep out keywords of your choice from an mp4 by leveraging a transcription model (here Whisper) to transcribe the audio, then target and replace chosen words with *bleep* sounds using the extracted timestamps associated with your chosen word(s).
All processing is performed locally - see the streamlit app (setup below) and detailed walkthrough notebook (see `beep_that_sht_walkthrough.ipynb`) to play / see nitty gritty details. Click [](https://huggingface.co/spaces/neonwatty/bleep_that_sht) to try out this toy app directly in your browser. WARNING: the machine this Space is running on is pretty small - so use it to try out shorter (<2min) videos.
Some examples of the end product (make sure to turn volume on, its off by default).
https://github.com/user-attachments/assets/da50f8a9-27ba-4747-92e0-72a25e65175c
Let's look more closely at the last example above - below is a short clip we'll bleep out some words from using the pipeline in this repo. (make sure to turn on audio - its off by default)
https://github.com/neonwatty/bleep_that_sht/assets/16326421/fb8568fe-aba0-49e2-a563-642d658c0651
Now the same clip with the words - "treetz", "ice", "cream", "chocolate", "syrup", and "cookie" - bleeped out
https://github.com/neonwatty/bleep_that_sht/assets/16326421/63ebd7a0-46f6-4efd-80ea-20512ff427c0
## Install instructions
To get setup to run the notebook / bleep your own videos / run the strealit demo first install the requirements for this project by pasting the below in your terminal.
```python
pip install -r requirements.streamlit
```
To install requirements for the gradio demo use this install
```python
pip install -r requirements.gradio
```
You will need [ffmpeg](https://www.ffmpeg.org/download.html) installed on your machine as well.
## Instructions for bleeping **youtube** videos via youtube / shorts url
Start this streamlit demo locally that lets you enter in a youtube / shorts url to a video you wish to bleep
```python
python -m streamlit run bleep_that_sht/app_url_download.py
```
Alternatively you can start a gradio server with the same functionality
```python
python -m bleep_that_sht/gradio_app_url_download.py
```
This is the version hosted in the HF space [](https://huggingface.co/spaces/neonwatty/bleep_that_sht).
## Instructions for bleeping your own **local** videos
Start this streamlit demo locally that lets you drag and drop local video files to bleep
```python
python -m streamlit run bleep_that_sht/app_video_upload.py
```