| Name | audiosr JSON |
| Version |
0.0.7
JSON |
| download |
| home_page | https://github.com/haoheliu/audiosr |
| Summary | This package is written for text-to-audio/music generation. |
| upload_time | 2024-02-05 14:26:25 |
| maintainer | |
| docs_url | None |
| author | Haohe Liu |
| requires_python | >=3.7.0 |
| license | MIT |
| keywords |
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# AudioSR: Versatile Audio Super-resolution at Scale
[](https://arxiv.org/abs/2309.07314) [](https://audioldm.github.io/audiosr) [](https://replicate.com/nateraw/audio-super-resolution)
Pass your audio in, AudioSR will make it high fidelity!
Work on all types of audio (e.g., music, speech, dog, raining, ...) & all sampling rates.
Share your thoughts/samples/issues in our discord channel: https://discord.gg/HWeBsJryaf
## Change Log
- 2023-09-24: Add replicate demo (@nateraw); Fix error on windows, librosa warning etc (@ORI-Muchim).
- 2023-09-16: Fix DC shift issue. Fix duration padding bug. Update default DDIM steps to 50.
## Commandline Usage
## Installation
```shell
# Optional
conda create -n audiosr python=3.9; conda activate audiosr
# Install AudioLDM
pip3 install audiosr==0.0.7
```
## Usage
Process a list of files. The result will be saved at ./output by default.
```shell
audiosr -il batch.lst
```
Process a single audio file.
```shell
audiosr -i example/music.wav
```
Full usage instruction
```shell
> audiosr -h
> usage: audiosr [-h] -i INPUT_AUDIO_FILE [-il INPUT_FILE_LIST] [-s SAVE_PATH] [--model_name {basic,speech}] [-d DEVICE] [--ddim_steps DDIM_STEPS] [-gs GUIDANCE_SCALE] [--seed SEED]
optional arguments:
-h, --help show this help message and exit
-i INPUT_AUDIO_FILE, --input_audio_file INPUT_AUDIO_FILE
Input audio file for audio super resolution
-il INPUT_FILE_LIST, --input_file_list INPUT_FILE_LIST
A file that contains all audio files that need to perform audio super resolution
-s SAVE_PATH, --save_path SAVE_PATH
The path to save model output
--model_name {basic,speech}
The checkpoint you gonna use
-d DEVICE, --device DEVICE
The device for computation. If not specified, the script will automatically choose the device based on your environment.
--ddim_steps DDIM_STEPS
The sampling step for DDIM
-gs GUIDANCE_SCALE, --guidance_scale GUIDANCE_SCALE
Guidance scale (Large => better quality and relavancy to text; Small => better diversity)
--seed SEED Change this value (any integer number) will lead to a different generation result.
--suffix SUFFIX Suffix for the output file
```
## TODO
[](https://www.buymeacoffee.com/haoheliuP)
- [ ] Add gradio demo.
- [ ] Optimize the inference speed.
## Cite our work
If you find this repo useful, please consider citing:
```bibtex
@article{liu2023audiosr,
title={{AudioSR}: Versatile Audio Super-resolution at Scale},
author={Liu, Haohe and Chen, Ke and Tian, Qiao and Wang, Wenwu and Plumbley, Mark D},
journal={arXiv preprint arXiv:2309.07314},
year={2023}
}
```
Raw data
{
"_id": null,
"home_page": "https://github.com/haoheliu/audiosr",
"name": "audiosr",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.7.0",
"maintainer_email": "",
"keywords": "",
"author": "Haohe Liu",
"author_email": "haoheliu@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/64/e5/78b6385ae7156697a3d04cf7e8fbb894f11ab8a95ebf6dd70bd4f49307ee/audiosr-0.0.7.tar.gz",
"platform": null,
"description": "\n\n# AudioSR: Versatile Audio Super-resolution at Scale\n\n[](https://arxiv.org/abs/2309.07314) [](https://audioldm.github.io/audiosr) [](https://replicate.com/nateraw/audio-super-resolution)\n\nPass your audio in, AudioSR will make it high fidelity! \n\nWork on all types of audio (e.g., music, speech, dog, raining, ...) & all sampling rates.\n\nShare your thoughts/samples/issues in our discord channel: https://discord.gg/HWeBsJryaf\n\n\n\n## Change Log\n- 2023-09-24: Add replicate demo (@nateraw); Fix error on windows, librosa warning etc (@ORI-Muchim). \n- 2023-09-16: Fix DC shift issue. Fix duration padding bug. Update default DDIM steps to 50.\n\n## Commandline Usage\n\n## Installation\n```shell\n# Optional\nconda create -n audiosr python=3.9; conda activate audiosr\n# Install AudioLDM\npip3 install audiosr==0.0.7\n```\n\n## Usage\n\nProcess a list of files. The result will be saved at ./output by default.\n\n```shell\naudiosr -il batch.lst\n```\n\nProcess a single audio file.\n```shell\naudiosr -i example/music.wav\n```\n\nFull usage instruction\n\n```shell\n> audiosr -h\n\n> usage: audiosr [-h] -i INPUT_AUDIO_FILE [-il INPUT_FILE_LIST] [-s SAVE_PATH] [--model_name {basic,speech}] [-d DEVICE] [--ddim_steps DDIM_STEPS] [-gs GUIDANCE_SCALE] [--seed SEED]\n\noptional arguments:\n -h, --help show this help message and exit\n -i INPUT_AUDIO_FILE, --input_audio_file INPUT_AUDIO_FILE\n Input audio file for audio super resolution\n -il INPUT_FILE_LIST, --input_file_list INPUT_FILE_LIST\n A file that contains all audio files that need to perform audio super resolution\n -s SAVE_PATH, --save_path SAVE_PATH\n The path to save model output\n --model_name {basic,speech}\n The checkpoint you gonna use\n -d DEVICE, --device DEVICE\n The device for computation. If not specified, the script will automatically choose the device based on your environment.\n --ddim_steps DDIM_STEPS\n The sampling step for DDIM\n -gs GUIDANCE_SCALE, --guidance_scale GUIDANCE_SCALE\n Guidance scale (Large => better quality and relavancy to text; Small => better diversity)\n --seed SEED Change this value (any integer number) will lead to a different generation result.\n --suffix SUFFIX Suffix for the output file\n```\n\n\n## TODO\n[](https://www.buymeacoffee.com/haoheliuP)\n\n- [ ] Add gradio demo.\n- [ ] Optimize the inference speed.\n\n## Cite our work\nIf you find this repo useful, please consider citing: \n```bibtex\n@article{liu2023audiosr,\n title={{AudioSR}: Versatile Audio Super-resolution at Scale},\n author={Liu, Haohe and Chen, Ke and Tian, Qiao and Wang, Wenwu and Plumbley, Mark D},\n journal={arXiv preprint arXiv:2309.07314},\n year={2023}\n}\n```\n\n\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "This package is written for text-to-audio/music generation.",
"version": "0.0.7",
"project_urls": {
"Homepage": "https://github.com/haoheliu/audiosr"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "7e12e53ffbe19d52d544ab7bcc4f1e0a691fd6ed5e4dc342ebc5a30fcbe519bf",
"md5": "5655d2dc5f26279defb604891a1b665d",
"sha256": "05794f995ab42458216eb302dd9768c1c1e535091ee54e9e09f69a60eaad96e2"
},
"downloads": -1,
"filename": "audiosr-0.0.7-py3-none-any.whl",
"has_sig": false,
"md5_digest": "5655d2dc5f26279defb604891a1b665d",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7.0",
"size": 2917295,
"upload_time": "2024-02-05T14:26:21",
"upload_time_iso_8601": "2024-02-05T14:26:21.753003Z",
"url": "https://files.pythonhosted.org/packages/7e/12/e53ffbe19d52d544ab7bcc4f1e0a691fd6ed5e4dc342ebc5a30fcbe519bf/audiosr-0.0.7-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "64e578b6385ae7156697a3d04cf7e8fbb894f11ab8a95ebf6dd70bd4f49307ee",
"md5": "39930c0f2f655fe5782219f6ae21d442",
"sha256": "6e272a00f6dfbb4ae7b749b8cc6c90f58e0f4aaf2f96ae7b1e5f58ddb8c75803"
},
"downloads": -1,
"filename": "audiosr-0.0.7.tar.gz",
"has_sig": false,
"md5_digest": "39930c0f2f655fe5782219f6ae21d442",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7.0",
"size": 2890038,
"upload_time": "2024-02-05T14:26:25",
"upload_time_iso_8601": "2024-02-05T14:26:25.595904Z",
"url": "https://files.pythonhosted.org/packages/64/e5/78b6385ae7156697a3d04cf7e8fbb894f11ab8a95ebf6dd70bd4f49307ee/audiosr-0.0.7.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-02-05 14:26:25",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "haoheliu",
"github_project": "audiosr",
"github_not_found": true,
"lcname": "audiosr"
}
