Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/tky823/audyn
https://github.com/tky823/audyn
Last synced: 10 days ago
JSON representation
- Host: GitHub
- URL: https://github.com/tky823/audyn
- Owner: tky823
- License: apache-2.0
- Created: 2023-08-11T14:52:06.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-11-24T16:14:32.000Z (about 2 months ago)
- Last Synced: 2024-12-28T23:55:36.073Z (12 days ago)
- Language: Python
- Homepage:
- Size: 2.75 MB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 30
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Audyn
[](https://codecov.io/gh/tky823/Audyn)
Audyn is PyTorch toolkit for audio synthesis.
## Build Status
| Python/PyTorch | Ubuntu | MacOS | Windows |
|:-:|:-:|:-:|:-:|
| 3.9/2.0 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.9_torch-2.0.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-13_python-3.9_torch-2.0.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_windows-latest_python-3.9_torch-2.0.yaml) |
| 3.9/2.1 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.9_torch-2.1.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-13_python-3.9_torch-2.1.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_windows-latest_python-3.9_torch-2.1.yaml) |
| 3.9/2.2 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.9_torch-2.2.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-13_python-3.9_torch-2.2.yaml) | |
| 3.9/2.3 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.9_torch-2.3.yaml) | | |
| 3.10/2.0 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.10_torch-2.0.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-13_python-3.10_torch-2.0.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_windows-latest_python-3.10_torch-2.0.yaml) |
| 3.10/2.1 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.10_torch-2.1.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-13_python-3.10_torch-2.1.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_windows-latest_python-3.10_torch-2.1.yaml) |
| 3.10/2.2 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.10_torch-2.2.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-13_python-3.10_torch-2.2.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_windows-latest_python-3.10_torch-2.2.yaml) |
| 3.10/2.3 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.10_torch-2.3.yaml) | | |
| 3.11/2.0 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.11_torch-2.0.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-13_python-3.11_torch-2.0.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_windows-latest_python-3.11_torch-2.0.yaml) |
| 3.11/2.1 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.11_torch-2.1.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-13_python-3.11_torch-2.1.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_windows-latest_python-3.11_torch-2.1.yaml) |
| 3.11/2.2 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.11_torch-2.2.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-13_python-3.11_torch-2.2.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_windows-latest_python-3.11_torch-2.2.yaml) |
| 3.11/2.3 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.11_torch-2.3.yaml) | | |
| 3.12/2.2 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.12_torch-2.2.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_macos-13_python-3.11_torch-2.2.yaml) | [](https://github.com/tky823/Audyn/actions/workflows/test_package_windows-latest_python-3.11_torch-2.2.yaml) |
| 3.12/2.3 | [](https://github.com/tky823/Audyn/actions/workflows/test_package_ubuntu-latest_python-3.11_torch-2.3.yaml) | | |
## Installation
You can install by pip.
```shell
pip install git+https://github.com/tky823/Audyn.git
```
or clone this repository.
```shell
git clone https://github.com/tky823/Audyn.git
cd Audyn
pip install -e .
```
If you need to run recipes, add `[recipes]` as follows:
```shell
# In Audyn/
pip install -e ".[recipes]"
```
If you use MacOS, you may need to set `MACOSX_DEPLOYMENT_TARGET` during installation to build C++ related modules.
### C++ extension
We use [C++ extension](https://pytorch.org/tutorials/advanced/cpp_extension.html) to search monotonic alignment in some models (e.g. GlowTTS).
To take full advantage of computational efficiency, set appropriate value of `OMP_NUM_THREADS` and `CXX` during installation:
```shell
# In Audyn/
export CXX= # e.g. /usr/bin/c++
export OMP_NUM_THREADS=
pip install -e "."
```
## Development
```shell
git clone https://github.com/tky823/Audyn.git
cd Audyn
pip install -e ".[recipes,dev,tests]"
```
## Build Documentation Locally (optional)
To build the documentation locally, you have to include `docs` when installing `Audyn`.
```shell
pip install -e ".[docs]"
```
When you build the documentation, run the following command.
```shell
cd docs/
make html
```
Or, you can build the documentation automatically using `sphinx-autobuild`.
```shell
# in Audyn/
sphinx-autobuild docs docs/_build/html
```
## Test
```shell
pytest tests/package
```
To include slow tests
```shell
pytest tests/package --runslow
```
## License
- Apache License, Version 2.0 **EXCEPT FOR WEIGHTS OF PRETRAINED MODELS**
- Weights for some of the pre-trained models are extracted from the official implementations. Their licenses follow the official implementations.