A vocal source separation
Project description
Vocal
A vocal source separation
pip install vocal
import librosa
import soundfile as sf
from vocal import get_model, separate_vocal
device = "cuda" # or cpu
audio, sr = librosa.load("audio.wav", sr=44100, mono=False)
model = get_model(device) # download model from HF
audio_data = separate_vocal(model, audio, device, silent=False)
sf.write("vocal.mp3", format="MP3", data=audio_data.T, samplerate=sr)
CLI
Sinlge file
vocali -i audio.mp3 -o output.mp3
Folder
vocali -i audio/ -o output --recursive
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
vocal-0.0.5.tar.gz
(5.4 kB
view details)
Built Distribution
File details
Details for the file vocal-0.0.5.tar.gz.
File metadata
- Download URL: vocal-0.0.5.tar.gz
- Upload date:
- Size: 5.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.8.19
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 09d7849b361cee7de8835a235af59f37a2d744e1ffa5c0da6d47752bfafa01a3 |
|
| MD5 | c8af5b657370a20acb08a87449f39ccf |
|
| BLAKE2b-256 | 535825c8e45831ec067766082dd2183a301bdf99970067278377bb9a24da8a01 |
File details
Details for the file vocal-0.0.5-py2.py3-none-any.whl.
File metadata
- Download URL: vocal-0.0.5-py2.py3-none-any.whl
- Upload date:
- Size: 5.3 kB
- Tags: Python 2, Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.8.19
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | c77913c2e8e93c39b581d3be5471c9ec73c87d70e33e3d8bef929f6a27d2d0cd |
|
| MD5 | 395da3c1d6615c70981c726e6246a430 |
|
| BLAKE2b-256 | f883b5f061fa0da6cbb896b2f0ee6ba6cfb6589a3e575dba98cc2fbc3b5d9d28 |
