From 4fcc009ef7e4cc53df8c8878ff7815f94ee37fc6 Mon Sep 17 00:00:00 2001 From: Christopher Landschoot Date: Thu, 16 May 2024 13:12:17 -0500 Subject: [PATCH] Moving image again and correcting reference. --- CHANGELOG.md | 5 +++++ README.md | 6 +++--- .../images => images}/frequency_weighting.png | Bin setup.cfg | 4 ++-- 4 files changed, 10 insertions(+), 5 deletions(-) rename {torch_log_wmse_audio_quality/images => images}/frequency_weighting.png (100%) diff --git a/CHANGELOG.md b/CHANGELOG.md index 97d9995..2abcc94 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -18,3 +18,8 @@ Error in tensor shapes. Was processing as the incorrect [batch, channels, stem, #### Include Image Moved frequency weighting image to be included in the package. + +## 0.1.4 (2024-05-16) + +#### Image Bug +Moving image again and correcting reference. diff --git a/README.md b/README.md index 99dc60c..f72c00a 100644 --- a/README.md +++ b/README.md @@ -65,9 +65,9 @@ The goal of this metric is to account for several factors not present in current ##### Frequency Weighting To measure the frequencies of a signal closer to that of human hearing, the following frequency weighting is applied. This helps the model effectively pay less attention to errors at frequencies that humans are not sensitive to (e.g. 50 Hz) and give more weight to those that we are acutely tuned to (e.g. 3kHz). -![Frequency Weighting](torch_log_wmse_audio_quality/images/frequency_weighting.png) +![Frequency Weighting](https://raw.githubusercontent.com/crlandsc/torch-log-wmse-audio-quality/main/images/frequency_weighting.png) -This metric has been constructed with high fidelity audio in mind (sample rates ≥ 44.1kHz). It theoretically could work for lower sample rates, like 16kHz, but the metric performs an internal resampling to 44.1kHz for consistency across any input sample rates. +This metric has been constructed with high-fidelity audio in mind (sample rates ≥ 44.1kHz). It theoretically could work for lower sample rates, like 16kHz, but the metric performs an internal resampling to 44.1kHz for consistency across any input sample rates. ##### Inputs Unlike many audio quality metrics, logWMSE accepts 3 audio inputs rather than 2: @@ -95,5 +95,5 @@ Contributions are welcome! Please open an issue or submit a pull request if you This project is licensed under the Apache License 2.0. See [LICENSE](LICENSE) for details. -## Acknowledgements +## Acknowledgments Thanks to [Whitebalance](https://www.whitebalance.co/) for backing this project. diff --git a/torch_log_wmse_audio_quality/images/frequency_weighting.png b/images/frequency_weighting.png similarity index 100% rename from torch_log_wmse_audio_quality/images/frequency_weighting.png rename to images/frequency_weighting.png diff --git a/setup.cfg b/setup.cfg index 16ba4be..6348f10 100644 --- a/setup.cfg +++ b/setup.cfg @@ -1,6 +1,6 @@ [metadata] name = torch-log-wmse-audio-quality -version = 0.1.3 +version = 0.1.4 author = Christopher Landschoot author_email = crlandschoot@gmail.com license = Apache License 2.0 @@ -25,7 +25,7 @@ install_requires = numpy>=1.23.5 [options.package_data] -torch_log_wmse_audio_quality = filter_ir.pkl, images/frequency_weighting.png +torch_log_wmse_audio_quality = filter_ir.pkl [options.packages.find] where = . \ No newline at end of file