gladia-torchaudio
Data manipulation and transformation for audio signal processing, powered by PyTorch
Science Score: 64.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
✓Academic publication links
Links to: zenodo.org -
✓Committers with academic emails
10 of 237 committers (4.2%) from academic institutions -
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (13.7%) to scientific vocabulary
Keywords
Keywords from Contributors
Repository
Data manipulation and transformation for audio signal processing, powered by PyTorch
Basic Info
- Host: GitHub
- Owner: pytorch
- License: bsd-2-clause
- Language: Python
- Default Branch: main
- Homepage: https://pytorch.org/audio
- Size: 1.62 GB
Statistics
- Stars: 2,723
- Watchers: 70
- Forks: 719
- Open Issues: 340
- Releases: 39
Topics
Metadata Files
README.md
torchaudio: an audio library for PyTorch
[!NOTE] We have transitioned TorchAudio into a maintenance phase. This process removed some user-facing features. These features were deprecated from TorchAudio 2.8 and removed in 2.9. Our main goals were to reduce redundancies with the rest of the PyTorch ecosystem, make it easier to maintain, and create a version of TorchAudio that is more tightly scoped to its strengths: processing audio data for ML. Please see our community message for more details.
The aim of torchaudio is to apply PyTorch to the audio domain. By supporting PyTorch, torchaudio follows the same philosophy of providing strong GPU acceleration, having a focus on trainable features through the autograd system, and having consistent style (tensor names and dimension names). Therefore, it is primarily a machine learning library and not a general signal processing library. The benefits of PyTorch can be seen in torchaudio through having all the computations be through PyTorch operations which makes it easy to use and feel like a natural extension.
- Dataloaders for common audio datasets
- Audio and speech processing functions
- Common audio transforms
- Compliance interfaces: Run code using PyTorch that align with other libraries
Installation
Please refer to https://pytorch.org/audio/main/installation.html for installation and build process of TorchAudio.
API Reference
API Reference is located here: http://pytorch.org/audio/main/
Contributing Guidelines
Please refer to CONTRIBUTING.md
Citation
If you find this package useful, please cite as:
bibtex
@article{yang2021torchaudio,
title={TorchAudio: Building Blocks for Audio and Speech Processing},
author={Yao-Yuan Yang and Moto Hira and Zhaoheng Ni and Anjali Chourdia and Artyom Astafurov and Caroline Chen and Ching-Feng Yeh and Christian Puhrsch and David Pollack and Dmitriy Genzel and Donny Greenberg and Edward Z. Yang and Jason Lian and Jay Mahadeokar and Jeff Hwang and Ji Chen and Peter Goldsborough and Prabhat Roy and Sean Narenthiran and Shinji Watanabe and Soumith Chintala and Vincent Quenneville-Bélair and Yangyang Shi},
journal={arXiv preprint arXiv:2110.15018},
year={2021}
}
bibtex
@misc{hwang2023torchaudio,
title={TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch},
author={Jeff Hwang and Moto Hira and Caroline Chen and Xiaohui Zhang and Zhaoheng Ni and Guangzhi Sun and Pingchuan Ma and Ruizhe Huang and Vineel Pratap and Yuekai Zhang and Anurag Kumar and Chin-Yun Yu and Chuang Zhu and Chunxi Liu and Jacob Kahn and Mirco Ravanelli and Peng Sun and Shinji Watanabe and Yangyang Shi and Yumeng Tao and Robin Scheibler and Samuele Cornell and Sean Kim and Stavros Petridis},
year={2023},
eprint={2310.17864},
archivePrefix={arXiv},
primaryClass={eess.AS}
}
Disclaimer on Datasets
This is a utility library that downloads and prepares public datasets. We do not host or distribute these datasets, vouch for their quality or fairness, or claim that you have license to use the dataset. It is your responsibility to determine whether you have permission to use the dataset under the dataset's license.
If you're a dataset owner and wish to update any part of it (description, citation, etc.), or do not want your dataset to be included in this library, please get in touch through a GitHub issue. Thanks for your contribution to the ML community!
Pre-trained Model License
The pre-trained models provided in this library may have their own licenses or terms and conditions derived from the dataset used for training. It is your responsibility to determine whether you have permission to use the models for your use case.
For instance, SquimSubjective model is released under the Creative Commons Attribution Non Commercial 4.0 International (CC-BY-NC 4.0) license. See the link for additional details.
Other pre-trained models that have different license are noted in documentation. Please checkout the documentation page.
Owner
- Name: pytorch
- Login: pytorch
- Kind: organization
- Location: where the eigens are valued
- Website: https://pytorch.org
- Repositories: 83
- Profile: https://github.com/pytorch
Citation (CITATION)
@misc{hwang2023torchaudio,
title={TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch},
author={Jeff Hwang and Moto Hira and Caroline Chen and Xiaohui Zhang and Zhaoheng Ni and Guangzhi Sun and Pingchuan Ma and Ruizhe Huang and Vineel Pratap and Yuekai Zhang and Anurag Kumar and Chin-Yun Yu and Chuang Zhu and Chunxi Liu and Jacob Kahn and Mirco Ravanelli and Peng Sun and Shinji Watanabe and Yangyang Shi and Yumeng Tao and Robin Scheibler and Samuele Cornell and Sean Kim and Stavros Petridis},
year={2023},
eprint={2310.17864},
archivePrefix={arXiv},
primaryClass={eess.AS}
}
GitHub Events
Total
- Create event: 90
- Issues event: 47
- Release event: 4
- Watch event: 212
- Delete event: 48
- Member event: 2
- Issue comment event: 335
- Push event: 643
- Pull request review comment event: 67
- Pull request review event: 115
- Pull request event: 213
- Fork event: 67
Last Year
- Create event: 90
- Issues event: 47
- Release event: 4
- Watch event: 212
- Delete event: 48
- Member event: 2
- Issue comment event: 335
- Push event: 643
- Pull request review comment event: 67
- Pull request review event: 115
- Pull request event: 213
- Fork event: 67
Committers
Last synced: 9 months ago
Top Committers
| Name | Commits | |
|---|---|---|
| moto | 8****k | 931 |
| Zhaoheng Ni | z****i@f****m | 173 |
| Caroline Chen | c****n@f****m | 127 |
| hwangjeff | i****g@g****m | 105 |
| Vincent QB | v****b | 89 |
| Andrey Talman | a****n@f****m | 64 |
| jamarshon | j****n@f****m | 56 |
| yangarbiter | y****r | 32 |
| Edward Z. Yang | e****g@f****m | 28 |
| Nikita Shulga | n****a@f****m | 27 |
| Omkar Salpekar | o****r@f****m | 26 |
| Krishna Kalyan | k****3@g****m | 26 |
| Eli Uriegas | 1****e | 25 |
| Bhargav Kathivarapu | b****1@g****m | 23 |
| David Pollack | d****d@d****t | 23 |
| Chin-Yun Yu | y****1@g****m | 22 |
| Tomás Osório | t****o@g****m | 22 |
| Sean Kim | s****4@f****m | 20 |
| jimchen90 | 6****0 | 19 |
| Aziz | a****6@g****m | 15 |
| Soumith Chintala | s****h@g****m | 15 |
| Nicolas Hug | n****g@f****m | 13 |
| moto-meta | 1****a | 12 |
| engineerchuan | e****n@g****m | 12 |
| Prabhat Roy | p****y@f****m | 11 |
| Matti Picus | m****s@g****m | 11 |
| Pingchuan Ma | p****6@i****k | 11 |
| Yi Zhang | z****i@m****m | 10 |
| Jcaw | t****w@g****m | 10 |
| Joao Gomes | j****s@f****m | 9 |
| and 207 more... | ||
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 6 months ago
All Time
- Total issues: 269
- Total pull requests: 606
- Average time to close issues: 8 months
- Average time to close pull requests: about 2 months
- Total issue authors: 205
- Total pull request authors: 108
- Average comments per issue: 3.15
- Average comments per pull request: 2.52
- Merged pull requests: 230
- Bot issues: 1
- Bot pull requests: 1
Past Year
- Issues: 48
- Pull requests: 232
- Average time to close issues: 12 days
- Average time to close pull requests: 5 days
- Issue authors: 40
- Pull request authors: 46
- Average comments per issue: 0.71
- Average comments per pull request: 1.58
- Merged pull requests: 100
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- mthrok (16)
- hkctkuy (8)
- vincentqb (6)
- atalman (5)
- pearu (5)
- pzelasko (4)
- nateanl (4)
- gau-nernst (3)
- yurivict (3)
- DanTremonti (3)
- w238liu (3)
- Mddct (2)
- eyalcohen308 (2)
- pedromoraesh (2)
- johnnynunez (2)
Pull Request Authors
- mthrok (146)
- samanklesaria (73)
- atalman (51)
- NicolasHug (39)
- nateanl (16)
- hwangjeff (13)
- ahmadsharif1 (13)
- moto-meta (11)
- osalpekar (10)
- r-barnes (8)
- kit1980 (8)
- facebook-github-bot (8)
- amd-sriram (7)
- mpc001 (7)
- RoyJames (6)
Top Labels
Issue Labels
Pull Request Labels
Packages
- Total packages: 6
-
Total downloads:
- pypi 10,104,529 last-month
- Total docker downloads: 12,723,776
-
Total dependent packages: 534
(may contain duplicates) -
Total dependent repositories: 11,395
(may contain duplicates) - Total versions: 218
- Total maintainers: 9
pypi.org: torchaudio
An audio package for PyTorch
- Homepage: https://github.com/pytorch/audio
- Documentation: https://torchaudio.readthedocs.io/
- License: BSD License
-
Latest release: 2.8.0
published 7 months ago
Rankings
proxy.golang.org: github.com/pytorch/audio
- Documentation: https://pkg.go.dev/github.com/pytorch/audio#section-documentation
- License: bsd-2-clause
-
Latest release: v2.8.0+incompatible
published 7 months ago
Rankings
spack.io: py-torchaudio
An audio package for PyTorch.
- Homepage: https://github.com/pytorch/audio
- License: []
-
Latest release: 0.4.0
published almost 4 years ago
Rankings
Maintainers (1)
pypi.org: gladiaio-torchaudio
An audio package for PyTorch
- Homepage: https://github.com/pytorch/audio
- Documentation: https://gladiaio-torchaudio.readthedocs.io/
- License: BSD License
-
Latest release: 2.1.0a0
published over 2 years ago
Rankings
Maintainers (1)
pypi.org: gladia-torchaudio
An audio package for PyTorch
- Homepage: https://github.com/pytorch/audio
- Documentation: https://gladia-torchaudio.readthedocs.io/
- License: BSD License
-
Latest release: 2.1.0a0
published over 2 years ago
Rankings
Maintainers (1)
anaconda.org: torchaudio
The aim of torchaudio is to apply PyTorch to the audio domain. By supporting PyTorch, torchaudio follows the same philosophy of providing strong GPU acceleration, having a focus on trainable features through the autograd system, and having consistent style (tensor names and dimension names). Therefore, it is primarily a machine learning library and not a general signal processing library. The benefits of PyTorch can be seen in torchaudio through having all the computations be through PyTorch operations which makes it easy to use and feel like a natural extension.
- Homepage: https://pytorch.org/audio/stable/index.html
- License: BSD-2-Clause
-
Latest release: 2.5.1
published about 1 year ago
Rankings
Dependencies
- actions/checkout v2 composite
- actions/checkout v3 composite
- actions/download-artifact v3 composite
- actions/checkout v2 composite
- actions/setup-python v2 composite
- actions/checkout v2 composite
- actions/setup-python v2 composite
- PySoundFile *
- dataclasses *
- expecttest *
- future *
- kaldi-io *
- parameterized *
- IPython *
- boto3 *
- cython *
- deep-phonemizer *
- librosa ==0.10.0
- mir_eval *
- pandas *
- pandoc *
- pesq *
- pystoi *
- sentencepiece *
- Jinja2 <3.1.0
- breathe ==4.34.0
- matplotlib <=3.8
- nbsphinx ==0.8.8
- pyparsing <3,>=2.0.2
- resampy ==0.2.2
- sphinx ==5.1.1
- sphinx_gallery ==0.11.1
- sphinxcontrib.bibtex ==2.4.2
- sphinxcontrib.katex ==0.8.6
- ffmpeg-python *
- opencv-python *
- scikit-image *
- tqdm *
- SoundFile *
- kaldi_io *
- torch *
- pytorch_package_dep *