NOTE: Not affiliated with original authors of UTMOS!
This is an unofficial Python package for UTMOS (UTokyo-SaruLab MOS Prediction System). This repository is based on the original code. The paper is available here.
UTMOS is designed for calculating the mean opinion score (MOS) for a given voice sample. It can be used to calculate audio quality for datasets.
The score is on a scale of 1 to 5. If you'd like a score on 1 to 100, just multiply the score by 20 (score * 20).
Example: new_score = round(score * 100, 2)
This implementation supports CPU, CUDA, and MPS, as well as ROCm if PyTorch is configured properly. This implementation will automatically use the GPU if available.
pip install utmos
utmos audio.wav
import utmos
model = utmos.Score() # The model will be automatically downloaded and will automatically utilize the GPU if available.
model.calculate_wav_file('audio_file.wav') # -> Float
# or model.calculate_wav(wav, sample_rate)
This software is licensed under the MIT license.
FAQs
UT-Sarulab MOS prediction system using SSL models
We found that utmos demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Security News
CAI is a new open source AI framework that automates penetration testing tasks like scanning and exploitation up to 3,600× faster than humans.
Security News
Deno 2.4 brings back bundling, improves dependency updates and telemetry, and makes the runtime more practical for real-world JavaScript projects.
Security News
CVEForecast.org uses machine learning to project a record-breaking surge in vulnerability disclosures in 2025.