Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,5 +9,51 @@ app_file: app.py
|
|
| 9 |
pinned: false
|
| 10 |
short_description: An agent for splitting song stems
|
| 11 |
---
|
|
|
|
| 12 |
|
| 13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
pinned: false
|
| 10 |
short_description: An agent for splitting song stems
|
| 11 |
---
|
| 12 |
+
# Music Stem Splitter
|
| 13 |
|
| 14 |
+
This Streamlit application separates music tracks into individual stems (vocals, drums, bass, and other instruments) using the Demucs AI model.
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
## Features
|
| 19 |
+
|
| 20 |
+
- Upload MP3, WAV, FLAC, or OGG audio files
|
| 21 |
+
- Separate audio into four stems: vocals, drums, bass, and other instruments
|
| 22 |
+
- Listen to separated stems directly in the browser
|
| 23 |
+
- View spectrograms for each stem
|
| 24 |
+
- Download individual stems for further use
|
| 25 |
+
|
| 26 |
+
## Demo
|
| 27 |
+
|
| 28 |
+
1. Upload an audio file using the file uploader
|
| 29 |
+
2. Click "Split into Stems" to process the audio
|
| 30 |
+
3. Navigate through the tabs to listen to each stem
|
| 31 |
+
4. Download stems individually with the provided links
|
| 32 |
+
|
| 33 |
+
## Technical Details
|
| 34 |
+
|
| 35 |
+
This application uses the Demucs v4 model (HT-Demucs) developed by Facebook AI Research to perform music source separation. The model leverages deep neural networks to identify and isolate different components of a music recording.
|
| 36 |
+
|
| 37 |
+
### Limitations
|
| 38 |
+
|
| 39 |
+
Due to Hugging Face Spaces resource constraints:
|
| 40 |
+
- Maximum file size: 100MB
|
| 41 |
+
- Maximum audio duration: 5 minutes
|
| 42 |
+
- Processing may take several minutes depending on server load
|
| 43 |
+
|
| 44 |
+
### Local Installation
|
| 45 |
+
|
| 46 |
+
To run this application locally:
|
| 47 |
+
|
| 48 |
+
```
|
| 49 |
+
git clone https://huggingface.co/spaces/username/music-stem-splitter
|
| 50 |
+
cd music-stem-splitter
|
| 51 |
+
pip install -r requirements.txt
|
| 52 |
+
streamlit run app.py
|
| 53 |
+
```
|
| 54 |
+
|
| 55 |
+
## Credits
|
| 56 |
+
|
| 57 |
+
- [Demucs](https://github.com/facebookresearch/demucs) by Facebook AI Research
|
| 58 |
+
- Built with [Streamlit](https://streamlit.io/)
|
| 59 |
+
- Hosted on [Hugging Face Spaces](https://huggingface.co/spaces)
|