utmos

Name	utmos JSON
Version	1.1.10 JSON
	download
home_page	https://github.com/ttseval/utmos
Summary	UT-Sarulab MOS prediction system using SSL models
upload_time	2024-05-08 00:43:21
maintainer	None
docs_url	None
author	mrfakename
requires_python	None
license	MIT
keywords
VCS
bugtrack_url
requirements	No requirements were recorded.
Travis-CI	No Travis.
coveralls test coverage	No coveralls.

            NOTE: Not affiliated with original authors of UTMOS!


# Unofficial UTMOS Python Package

This is an unofficial Python package for **UTMOS (UTokyo-SaruLab MOS Prediction System)**. This repository is based on the [original code](https://github.com/sarulab-speech/UTMOS22). The paper is available [here](https://arxiv.org/abs/2204.02152).

## What is UTMOS?

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.

## Note

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)`

## Support

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.

## Installation

```bash
pip install utmos
```

## Usage

### CLI (Command Line Interface)

```bash
utmos audio.wav
```

### Python API

```python
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)
```

## License

This software is licensed under the MIT license.

            

Raw data

            {
    "_id": null,
    "home_page": "https://github.com/ttseval/utmos",
    "name": "utmos",
    "maintainer": null,
    "docs_url": null,
    "requires_python": null,
    "maintainer_email": null,
    "keywords": null,
    "author": "mrfakename",
    "author_email": "me@mrfake.name",
    "download_url": "https://files.pythonhosted.org/packages/19/dc/d248e9776ee7ae8a439d3ba70011b208cef86d28a91d96455de13adb98e1/utmos-1.1.10.tar.gz",
    "platform": null,
    "description": "NOTE: Not affiliated with original authors of UTMOS!\n\n\n# Unofficial UTMOS Python Package\n\nThis is an unofficial Python package for **UTMOS (UTokyo-SaruLab MOS Prediction System)**. This repository is based on the [original code](https://github.com/sarulab-speech/UTMOS22). The paper is available [here](https://arxiv.org/abs/2204.02152).\n\n## What is UTMOS?\n\nUTMOS is designed for calculating the mean opinion score (MOS) for a given voice sample. It can be used to calculate audio quality for datasets.\n\n## Note\n\nThe 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`).\n\nExample: `new_score = round(score * 100, 2)`\n\n## Support\n\nThis implementation supports CPU, CUDA, and MPS, as well as ROCm if PyTorch is configured properly. This implementation will automatically use the GPU if available.\n\n## Installation\n\n```bash\npip install utmos\n```\n\n## Usage\n\n### CLI (Command Line Interface)\n\n```bash\nutmos audio.wav\n```\n\n### Python API\n\n```python\nimport utmos\nmodel = utmos.Score() # The model will be automatically downloaded and will automatically utilize the GPU if available.\nmodel.calculate_wav_file('audio_file.wav') # -> Float\n# or model.calculate_wav(wav, sample_rate)\n```\n\n## License\n\nThis software is licensed under the MIT license.\n",
    "bugtrack_url": null,
    "license": "MIT",
    "summary": "UT-Sarulab MOS prediction system using SSL models",
    "version": "1.1.10",
    "project_urls": {
        "Homepage": "https://github.com/ttseval/utmos"
    },
    "split_keywords": [],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "452b92e89033000755d437239da84e062eeeae464cbaafa2bc52ff028c609b84",
                "md5": "4239a4d9b91c106724045cfa4b040b35",
                "sha256": "551b84c33a3dc0c5175cd7ca83839efdace5d4ac60fbf041b8680bb91151df60"
            },
            "downloads": -1,
            "filename": "utmos-1.1.10-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "4239a4d9b91c106724045cfa4b040b35",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": null,
            "size": 9665,
            "upload_time": "2024-05-08T00:43:20",
            "upload_time_iso_8601": "2024-05-08T00:43:20.351528Z",
            "url": "https://files.pythonhosted.org/packages/45/2b/92e89033000755d437239da84e062eeeae464cbaafa2bc52ff028c609b84/utmos-1.1.10-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "19dcd248e9776ee7ae8a439d3ba70011b208cef86d28a91d96455de13adb98e1",
                "md5": "624ddd51f4a83e209f702d13391967cd",
                "sha256": "0141a1dbbdd65f8f62d17de63b29a045d0aed47e0e7a35081dd60dc60fc33f86"
            },
            "downloads": -1,
            "filename": "utmos-1.1.10.tar.gz",
            "has_sig": false,
            "md5_digest": "624ddd51f4a83e209f702d13391967cd",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 7877,
            "upload_time": "2024-05-08T00:43:21",
            "upload_time_iso_8601": "2024-05-08T00:43:21.599692Z",
            "url": "https://files.pythonhosted.org/packages/19/dc/d248e9776ee7ae8a439d3ba70011b208cef86d28a91d96455de13adb98e1/utmos-1.1.10.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2024-05-08 00:43:21",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "github_user": "ttseval",
    "github_project": "utmos",
    "travis_ci": false,
    "coveralls": false,
    "github_actions": true,
    "lcname": "utmos"
}