# AudioLoader
AudioLoader is a PyTorch dataset based on [torchaudio](https://pytorch.org/audio/stable/datasets.html). It contains a collection of datasets that are not available in [torchaudio](https://pytorch.org/audio/stable/datasets.html) yet.
**Currently supported datasets:**
1. [Speech](./AudioLoader/speech/speech_README.md#Speech)
1. [Multilingual LibriSpeech (MLS)](./AudioLoader/speech/speech_README.md#Multilingual-LibriSpeech)
1. [TIMIT](./AudioLoader/speech/speech_README.md#TIMIT)
1. [SpeechCommands v2 (12 classes)](./AudioLoader/speech/speech_README.md#SpeechCommandsv2)
1. [Automatic Music Transcription (AMT)](./AudioLoader/music/amt_README.md#Automatic-Music-Transcription)
1. [MAPS](./AudioLoader/music/amt_README.md#maps)
1. [MusicNet](./AudioLoader/music/amt_README.md#musicnet)
1. [MAESTRO](./AudioLoader/music/amt_README.md#maestro)
1. [Music Source Separation (MSS)](./AudioLoader/music/mss/mss_README.md#Music-Source-Separation)
1. [FastMUSDB](./AudioLoader/music/mss/mss_README.md#FastMUSDB)
1. [MusdbHQ](./AudioLoader/music/mss/mss_README.md#MusdbHQ)
## Example code
A complete example code is available in this [repository](https://github.com/KinWaiCheuk/pytorch_template). The following pseudo code shows the general idea of how to apply AudioLoader to your existing code.
```python
from AudioLoader.speech import TIMIT
from torch.utils.data import DataLoader
# AudioLoader helps you to set up supported datasets
dataset = TIMIT('./YourFolder',
split='train',
groups='all',
download=True)
train_loader = DataLoader(dataset,
batch_size=4)
# Pass the dataset to you
model = MyModel()
trainer = pl.Trainer()
trainer.fit(model, train_loader)
```
## Installation
`pip install git+https://github.com/KinWaiCheuk/AudioLoader.git`
## News & Changelog
**version 0.0.3** (10 Sep 2021):
1. Replace broken links with a working links for `MAPS` and `TIMIT`
1. Remove the slience indicators in the phonemic labels for TIMIT
Raw data
{
"_id": null,
"home_page": "https://github.com/KinWaiCheuk/AudioLoader",
"name": "AudioLoader",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.6",
"maintainer_email": "",
"keywords": "",
"author": "KinWaiCheuk",
"author_email": "u3500684@connect.hku.hk",
"download_url": "https://files.pythonhosted.org/packages/78/50/26f3c21d9916006fd649cda7a6c46ce24eaa4d117f3839c00e5785df38df/AudioLoader-0.1.4.tar.gz",
"platform": null,
"description": "# AudioLoader\nAudioLoader is a PyTorch dataset based on [torchaudio](https://pytorch.org/audio/stable/datasets.html). It contains a collection of datasets that are not available in [torchaudio](https://pytorch.org/audio/stable/datasets.html) yet.\n\n**Currently supported datasets:**\n1. [Speech](./AudioLoader/speech/speech_README.md#Speech)\n 1. [Multilingual LibriSpeech (MLS)](./AudioLoader/speech/speech_README.md#Multilingual-LibriSpeech)\n 1. [TIMIT](./AudioLoader/speech/speech_README.md#TIMIT)\n 1. [SpeechCommands v2 (12 classes)](./AudioLoader/speech/speech_README.md#SpeechCommandsv2)\n1. [Automatic Music Transcription (AMT)](./AudioLoader/music/amt_README.md#Automatic-Music-Transcription)\n 1. [MAPS](./AudioLoader/music/amt_README.md#maps)\n 1. [MusicNet](./AudioLoader/music/amt_README.md#musicnet)\n 1. [MAESTRO](./AudioLoader/music/amt_README.md#maestro)\n1. [Music Source Separation (MSS)](./AudioLoader/music/mss/mss_README.md#Music-Source-Separation)\n 1. [FastMUSDB](./AudioLoader/music/mss/mss_README.md#FastMUSDB)\n 1. [MusdbHQ](./AudioLoader/music/mss/mss_README.md#MusdbHQ)\n \n## Example code\nA complete example code is available in this [repository](https://github.com/KinWaiCheuk/pytorch_template). The following pseudo code shows the general idea of how to apply AudioLoader to your existing code.\n\n```python\nfrom AudioLoader.speech import TIMIT\nfrom torch.utils.data import DataLoader\n\n# AudioLoader helps you to set up supported datasets\ndataset = TIMIT('./YourFolder',\n split='train',\n groups='all',\n download=True)\ntrain_loader = DataLoader(dataset,\n batch_size=4)\n\n# Pass the dataset to you \nmodel = MyModel()\ntrainer = pl.Trainer()\ntrainer.fit(model, train_loader)\n\n```\n\n## Installation\n`pip install git+https://github.com/KinWaiCheuk/AudioLoader.git`\n\n## News & Changelog\n**version 0.0.3** (10 Sep 2021): \n1. Replace broken links with a working links for `MAPS` and `TIMIT`\n1. Remove the slience indicators in the phonemic labels for TIMIT\n\n\n\n",
"bugtrack_url": null,
"license": "",
"summary": "A collection of PyTorch audio datasets for speech and music applications",
"version": "0.1.4",
"project_urls": {
"Homepage": "https://github.com/KinWaiCheuk/AudioLoader"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "801f0d642a538075173d58273bc5168365002e5c12f65454e18b4d76ffb94907",
"md5": "19aecc1eab930b6afa1c8705e43b4f35",
"sha256": "2e853ab04a1f48d94da948ee4bdee8e56671adf8523b597980b1d63091344e1b"
},
"downloads": -1,
"filename": "AudioLoader-0.1.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "19aecc1eab930b6afa1c8705e43b4f35",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.6",
"size": 48824,
"upload_time": "2023-08-08T09:55:54",
"upload_time_iso_8601": "2023-08-08T09:55:54.489992Z",
"url": "https://files.pythonhosted.org/packages/80/1f/0d642a538075173d58273bc5168365002e5c12f65454e18b4d76ffb94907/AudioLoader-0.1.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "785026f3c21d9916006fd649cda7a6c46ce24eaa4d117f3839c00e5785df38df",
"md5": "222b5ac1612eb20584d2d72ede8d40bd",
"sha256": "156e7a51585ddc6c6eba639261d0e58fc7d460a7730a461beb932804b8f4db8b"
},
"downloads": -1,
"filename": "AudioLoader-0.1.4.tar.gz",
"has_sig": false,
"md5_digest": "222b5ac1612eb20584d2d72ede8d40bd",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.6",
"size": 39939,
"upload_time": "2023-08-08T09:55:56",
"upload_time_iso_8601": "2023-08-08T09:55:56.263267Z",
"url": "https://files.pythonhosted.org/packages/78/50/26f3c21d9916006fd649cda7a6c46ce24eaa4d117f3839c00e5785df38df/AudioLoader-0.1.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-08-08 09:55:56",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "KinWaiCheuk",
"github_project": "AudioLoader",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [],
"lcname": "audioloader"
}
JSON
