A Self-Supervised Learning Library
Project description
MK-SSL
MK-SSL is a modular and extensible Self-Supervised Learning (SSL) toolbox focused on audio and multimodal representation learning.
🚧 This project is under active development. More details and documentation coming soon!
🔧 Installation
# (Coming soon)
📂 Project Structure
MK_SSL/
│
├── audio/
│ ├── models/
│ ├── datasets/
│ └── ...
├── vision/
├── multimodal/
├── trainer/
├── configs/
└── ...
📜 License
This project is released under the MIT License.
Stay tuned for more updates!
🧪 Usage Examples (Coming Soon)
from MK_SSL.audio.models import SimCLRSpeech
model = SimCLRSpeech(variant="base")
# model.forward(...)
📦 Model Zoo (Coming Soon)
Pretrained checkpoints and their benchmarks will be published here.
🙌 Contributing
Contributions are welcome! If you'd like to add a new model or feature, please open an issue or pull request.
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file mk_ssl-0.1.0.tar.gz.
File metadata
- Download URL: mk_ssl-0.1.0.tar.gz
- Upload date:
- Size: 148.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
23f927c8c9c13f0125cf02ebd2e8ac3081ee498d8da125e0b8f6e4a853728218
|
|
| MD5 |
b0a5d0277cf1741fa7ce8455578058bb
|
|
| BLAKE2b-256 |
60ee4ed88432550177bda066d8d77093adb8b38d61a4e9b7cc9cfd0b6adf676c
|
File details
Details for the file mk_ssl-0.1.0-py3-none-any.whl.
File metadata
- Download URL: mk_ssl-0.1.0-py3-none-any.whl
- Upload date:
- Size: 193.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
11d7d065545a2e56c5514293b52fed88bbd4f198574968830a95408a18817412
|
|
| MD5 |
515785d6b3ad2c66c8d8b8535c3b501d
|
|
| BLAKE2b-256 |
0caba1909662fe12409a5bdb44000f50ad261e402c3b74a75a5b20ae8ab77944
|
