| Name | torch-mdct JSON |
| Version |
0.4.1
JSON |
| download |
| home_page | None |
| Summary | A PyTorch implementation of the Modified Discrete Cosine Transform (MDCT) and its inverse for audio processing. |
| upload_time | 2024-12-17 10:40:54 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.8 |
| license | None |
| keywords |
audio
imdct
mdct
pytorch
signal processing
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# torch_mdct
A PyTorch implementation of the Modified Discrete Cosine Transform (MDCT) and its inverse for audio processing.
## Installation
```bash
pip install torch_mdct
```
## Usage
```python
import torchaudio
from torch_mdct import IMDCT, MDCT, kaiser_bessel_derived, vorbis
# Load a sample waveform
waveform, sample_rate = torchaudio.load("/path/to/audio.file")
# Initialize the mdct and imdct transforms
mdct = MDCT(win_length=1024, window_fn=vorbis, window_kwargs=None, center=True)
imdct = IMDCT(win_length=1024, window_fn=vorbis, window_kwargs=None, center=True)
# Transform waveform into mdct spectrogram
spectrogram = mdct(waveform)
# Transform spectrogram back to audio
reconst_waveform = imdct(spectrogram)
# Compute the differences
print(f"L1: {(waveform - reconst_waveform).abs().mean()}")
```
## References
[[1]](https://github.com/zafarrafii/Zaf-Python) Zaf-Python: Zafar's Audio Functions in **Python** for audio signal analysis.
[[2]](https://github.com/nils-werner/mdct) MDCT: A fast MDCT implementation using SciPy and FFTs.
Raw data
{
"_id": null,
"home_page": null,
"name": "torch-mdct",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "audio, imdct, mdct, pytorch, signal processing",
"author": null,
"author_email": "Kinyugo Maina <kinyugomaina@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/e9/6d/a65d5e09b791833493cf3b3b017d29b00f567f880a704fd518585c9f8c4c/torch_mdct-0.4.1.tar.gz",
"platform": null,
"description": "# torch_mdct\n\nA PyTorch implementation of the Modified Discrete Cosine Transform (MDCT) and its inverse for audio processing.\n\n## Installation \n\n```bash\npip install torch_mdct\n```\n\n## Usage\n\n```python\nimport torchaudio\nfrom torch_mdct import IMDCT, MDCT, kaiser_bessel_derived, vorbis\n\n# Load a sample waveform \nwaveform, sample_rate = torchaudio.load(\"/path/to/audio.file\")\n\n# Initialize the mdct and imdct transforms\nmdct = MDCT(win_length=1024, window_fn=vorbis, window_kwargs=None, center=True)\nimdct = IMDCT(win_length=1024, window_fn=vorbis, window_kwargs=None, center=True)\n\n# Transform waveform into mdct spectrogram\nspectrogram = mdct(waveform)\n\n# Transform spectrogram back to audio \nreconst_waveform = imdct(spectrogram)\n\n# Compute the differences\nprint(f\"L1: {(waveform - reconst_waveform).abs().mean()}\")\n```\n\n## References \n[[1]](https://github.com/zafarrafii/Zaf-Python) Zaf-Python: Zafar's Audio Functions in **Python** for audio signal analysis.\n\n[[2]](https://github.com/nils-werner/mdct) MDCT: A fast MDCT implementation using SciPy and FFTs.",
"bugtrack_url": null,
"license": null,
"summary": "A PyTorch implementation of the Modified Discrete Cosine Transform (MDCT) and its inverse for audio processing.",
"version": "0.4.1",
"project_urls": {
"Homepage": "https://github.com/Kinyugo/torch_mdct",
"Issues": "https://github.com/Kinyugo/torch_mdct/issues"
},
"split_keywords": [
"audio",
" imdct",
" mdct",
" pytorch",
" signal processing"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "28cd28f348cfb3590946b5929acbfc80669da49050a8871b91c2206386c98928",
"md5": "5a040c02b1e185e91c5bcdd9f7e3fd99",
"sha256": "67a3863260ba7115e55e15e6cef02d19c343d3f0ecd32f8a16e8626663078c5d"
},
"downloads": -1,
"filename": "torch_mdct-0.4.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "5a040c02b1e185e91c5bcdd9f7e3fd99",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 6239,
"upload_time": "2024-12-17T10:40:49",
"upload_time_iso_8601": "2024-12-17T10:40:49.343521Z",
"url": "https://files.pythonhosted.org/packages/28/cd/28f348cfb3590946b5929acbfc80669da49050a8871b91c2206386c98928/torch_mdct-0.4.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "e96da65d5e09b791833493cf3b3b017d29b00f567f880a704fd518585c9f8c4c",
"md5": "ae88a53e8cb3f8e5e33bdfcd620edd2c",
"sha256": "61282b3679b07a8a4671601d9251d9a74e2cf1a24eab4fd51eae707d9d6c6137"
},
"downloads": -1,
"filename": "torch_mdct-0.4.1.tar.gz",
"has_sig": false,
"md5_digest": "ae88a53e8cb3f8e5e33bdfcd620edd2c",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 3025737,
"upload_time": "2024-12-17T10:40:54",
"upload_time_iso_8601": "2024-12-17T10:40:54.289618Z",
"url": "https://files.pythonhosted.org/packages/e9/6d/a65d5e09b791833493cf3b3b017d29b00f567f880a704fd518585c9f8c4c/torch_mdct-0.4.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-12-17 10:40:54",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "Kinyugo",
"github_project": "torch_mdct",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "torch-mdct"
}
