2023-01-09T20:12:09,517 Created temporary directory: /tmp/pip-ephem-wheel-cache-h44w2uyb 2023-01-09T20:12:09,521 Created temporary directory: /tmp/pip-build-tracker-60izmwaz 2023-01-09T20:12:09,522 Initialized build tracking at /tmp/pip-build-tracker-60izmwaz 2023-01-09T20:12:09,522 Created build tracker: /tmp/pip-build-tracker-60izmwaz 2023-01-09T20:12:09,522 Entered build tracker: /tmp/pip-build-tracker-60izmwaz 2023-01-09T20:12:09,524 Created temporary directory: /tmp/pip-wheel-uvgw5fyc 2023-01-09T20:12:09,531 DEPRECATION: --no-binary currently disables reading from the cache of locally built wheels. In the future --no-binary will not influence the wheel cache. pip 23.1 will enforce this behaviour change. A possible replacement is to use the --no-cache-dir option. You can use the flag --use-feature=no-binary-enable-wheel-cache to test the upcoming behaviour. Discussion can be found at https://github.com/pypa/pip/issues/11453 2023-01-09T20:12:09,537 Created temporary directory: /tmp/pip-ephem-wheel-cache-ex5zfchb 2023-01-09T20:12:09,594 Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple 2023-01-09T20:12:09,601 2 location(s) to search for versions of auraloss: 2023-01-09T20:12:09,601 * https://pypi.org/simple/auraloss/ 2023-01-09T20:12:09,601 * https://www.piwheels.org/simple/auraloss/ 2023-01-09T20:12:09,603 Fetching project page and analyzing links: https://pypi.org/simple/auraloss/ 2023-01-09T20:12:09,604 Getting page https://pypi.org/simple/auraloss/ 2023-01-09T20:12:09,607 Found index url https://pypi.org/simple 2023-01-09T20:12:09,826 Fetched page https://pypi.org/simple/auraloss/ as application/vnd.pypi.simple.v1+json 2023-01-09T20:12:09,833 Skipping link: No binaries permitted for auraloss: https://files.pythonhosted.org/packages/d6/25/55d1e56d2cc1431a01b73d0df97deb1e387bd5d6543bf898fc1ee49634f0/auraloss-0.1.7-py3-none-any.whl (from https://pypi.org/simple/auraloss/) (requires-python:>=3.6.0) 2023-01-09T20:12:09,834 Found link https://files.pythonhosted.org/packages/ef/0b/396f1e34d6cdeba43cc31f31706c8ccf4cffbd3962ce8f5b14d7d720eb6b/auraloss-0.1.7.tar.gz (from https://pypi.org/simple/auraloss/) (requires-python:>=3.6.0), version: 0.1.7 2023-01-09T20:12:09,835 Skipping link: No binaries permitted for auraloss: https://files.pythonhosted.org/packages/01/e5/1f1ab8c0631707d528d50a531e826ce13cfcba459e69e379e98901486a33/auraloss-0.2.0-py3-none-any.whl (from https://pypi.org/simple/auraloss/) (requires-python:>=3.6.0) 2023-01-09T20:12:09,837 Found link https://files.pythonhosted.org/packages/ae/d6/4e108da932bc2de10a5a236622f95320bd1acbc28f650dd28b56e5011a1c/auraloss-0.2.0.tar.gz (from https://pypi.org/simple/auraloss/) (requires-python:>=3.6.0), version: 0.2.0 2023-01-09T20:12:09,837 Skipping link: No binaries permitted for auraloss: https://files.pythonhosted.org/packages/3e/ed/3dfb1909bef29478d9a22766eb74cc8e407f314eefe6bd218cdc24ea7680/auraloss-0.2.1-py3-none-any.whl (from https://pypi.org/simple/auraloss/) (requires-python:>=3.6.0) 2023-01-09T20:12:09,839 Found link https://files.pythonhosted.org/packages/80/fc/b0743001e5afa92a93e5b13b0f74f64b8450bcb263a71d649340d889ba11/auraloss-0.2.1.tar.gz (from https://pypi.org/simple/auraloss/) (requires-python:>=3.6.0), version: 0.2.1 2023-01-09T20:12:09,839 Skipping link: No binaries permitted for auraloss: https://files.pythonhosted.org/packages/11/b6/d3a792035cc21b55c22a8745ca9f4ea3835b2408d63d4c787dcf52e1af4a/auraloss-0.2.2-py3-none-any.whl (from https://pypi.org/simple/auraloss/) (requires-python:>=3.6.0) 2023-01-09T20:12:09,841 Found link https://files.pythonhosted.org/packages/d1/0c/88c8f0579631fb88119895fc13ed30fedcadfce80df97c179331568aa4bb/auraloss-0.2.2.tar.gz (from https://pypi.org/simple/auraloss/) (requires-python:>=3.6.0), version: 0.2.2 2023-01-09T20:12:09,841 Skipping link: No binaries permitted for auraloss: https://files.pythonhosted.org/packages/62/9c/7f19f53c92ba04a2a6c26f0d8388eed78bc8408f8ab8221d4ac7d2892468/auraloss-0.3.0-py3-none-any.whl (from https://pypi.org/simple/auraloss/) (requires-python:>=3.6.0) 2023-01-09T20:12:09,843 Found link https://files.pythonhosted.org/packages/1e/6e/0b8c140e51450b9f558bf9483500989d9b81e0bc99073b38743cb6739a15/auraloss-0.3.0.tar.gz (from https://pypi.org/simple/auraloss/) (requires-python:>=3.6.0), version: 0.3.0 2023-01-09T20:12:09,844 Fetching project page and analyzing links: https://www.piwheels.org/simple/auraloss/ 2023-01-09T20:12:09,844 Getting page https://www.piwheels.org/simple/auraloss/ 2023-01-09T20:12:09,847 Found index url https://www.piwheels.org/simple 2023-01-09T20:12:10,081 Fetched page https://www.piwheels.org/simple/auraloss/ as text/html 2023-01-09T20:12:10,085 Skipping link: No binaries permitted for auraloss: https://www.piwheels.org/simple/auraloss/auraloss-0.2.1-py3-none-any.whl#sha256=e21e1605a3c5f3ae7a19055d5de5fa28cb90c2a678d43d2ce391580e6e201596 (from https://www.piwheels.org/simple/auraloss/) (requires-python:>=3.6.0) 2023-01-09T20:12:10,086 Skipping link: No binaries permitted for auraloss: https://www.piwheels.org/simple/auraloss/auraloss-0.2.0-py3-none-any.whl#sha256=95ca26690ed697a0899bb04f1b4eac0ed44b4ef0d30c8f1ea264986dc3a076dc (from https://www.piwheels.org/simple/auraloss/) (requires-python:>=3.6.0) 2023-01-09T20:12:10,087 Skipping link: No binaries permitted for auraloss: https://www.piwheels.org/simple/auraloss/auraloss-0.1.7-py3-none-any.whl#sha256=aea15bde8ba4cacff0bfeeb9822acd8168ddd5e044b063b4d4ad813f3663e5df (from https://www.piwheels.org/simple/auraloss/) (requires-python:>=3.6.0) 2023-01-09T20:12:10,087 Skipping link: not a file: https://www.piwheels.org/simple/auraloss/ 2023-01-09T20:12:10,088 Skipping link: not a file: https://pypi.org/simple/auraloss/ 2023-01-09T20:12:10,125 Given no hashes to check 1 links for project 'auraloss': discarding no candidates 2023-01-09T20:12:10,155 Collecting auraloss==0.3.0 2023-01-09T20:12:10,160 Created temporary directory: /tmp/pip-unpack-p1f9nw_a 2023-01-09T20:12:10,392 Downloading auraloss-0.3.0.tar.gz (15 kB) 2023-01-09T20:12:10,477 Added auraloss==0.3.0 from https://files.pythonhosted.org/packages/1e/6e/0b8c140e51450b9f558bf9483500989d9b81e0bc99073b38743cb6739a15/auraloss-0.3.0.tar.gz to build tracker '/tmp/pip-build-tracker-60izmwaz' 2023-01-09T20:12:10,488 Created temporary directory: /tmp/pip-build-env-4fuq3jq4 2023-01-09T20:12:10,500 Installing build dependencies: started 2023-01-09T20:12:10,502 Running command pip subprocess to install build dependencies 2023-01-09T20:12:13,225 Using pip 22.3 from /home/piwheels/.local/lib/python3.7/site-packages/pip (python 3.7) 2023-01-09T20:12:14,017 DEPRECATION: --no-binary currently disables reading from the cache of locally built wheels. In the future --no-binary will not influence the wheel cache. pip 23.1 will enforce this behaviour change. A possible replacement is to use the --no-cache-dir option. You can use the flag --use-feature=no-binary-enable-wheel-cache to test the upcoming behaviour. Discussion can be found at https://github.com/pypa/pip/issues/11453 2023-01-09T20:12:14,071 Looking in indexes: https://pypi.org/simple, https://www.piwheels.org/simple 2023-01-09T20:12:17,864 Collecting setuptools 2023-01-09T20:12:18,135 Using cached https://www.piwheels.org/simple/setuptools/setuptools-65.6.3-py3-none-any.whl (1.2 MB) 2023-01-09T20:12:18,798 Collecting wheel 2023-01-09T20:12:18,834 Using cached https://www.piwheels.org/simple/wheel/wheel-0.38.4-py3-none-any.whl (36 kB) 2023-01-09T20:12:19,124 Collecting attrs 2023-01-09T20:12:19,160 Using cached https://www.piwheels.org/simple/attrs/attrs-22.2.0-py3-none-any.whl (60 kB) 2023-01-09T20:12:25,144 Installing collected packages: wheel, setuptools, attrs 2023-01-09T20:12:25,421 Creating /tmp/pip-build-env-4fuq3jq4/overlay/bin 2023-01-09T20:12:25,425 changing mode of /tmp/pip-build-env-4fuq3jq4/overlay/bin/wheel to 755 2023-01-09T20:12:30,626 Successfully installed attrs-22.2.0 setuptools-65.6.3 wheel-0.38.4 2023-01-09T20:12:30,659 [notice] A new release of pip available: 22.3 -> 22.3.1 2023-01-09T20:12:30,659 [notice] To update, run: python3 -m pip install --upgrade pip 2023-01-09T20:12:31,100 Installing build dependencies: finished with status 'done' 2023-01-09T20:12:31,112 Getting requirements to build wheel: started 2023-01-09T20:12:31,114 Running command Getting requirements to build wheel 2023-01-09T20:12:33,038 /tmp/pip-build-env-4fuq3jq4/overlay/lib/python3.7/site-packages/setuptools/config/_apply_pyprojecttoml.py:103: _WouldIgnoreField: 'readme' defined outside of `pyproject.toml` would be ignored. 2023-01-09T20:12:33,039 !! 2023-01-09T20:12:33,040 ########################################################################## 2023-01-09T20:12:33,041 # configuration would be ignored/result in error due to `pyproject.toml` # 2023-01-09T20:12:33,041 ########################################################################## 2023-01-09T20:12:33,042 The following seems to be defined outside of `pyproject.toml`: 2023-01-09T20:12:33,042 `readme = '\n
\n\n# auraloss\n\n\n\nA collection of audio-focused loss functions in PyTorch. \n\n[[PDF](https://www.christiansteinmetz.com/s/DMRN15__auraloss__Audio_focused_loss_functions_in_PyTorch.pdf)]\n\n
\n\n## Setup\n\n```\npip install auraloss\n```\n\nIf you want to use `MelSTFTLoss()` or `FIRFilter()` you will need to specify the extra install (librosa and scipy).\n\n```\npip install auraloss[all]\n```\n\n## Usage\n\n```python\nimport torch\nimport auraloss\n\nmrstft = auraloss.freq.MultiResolutionSTFTLoss()\n\ninput = torch.rand(8,1,44100)\ntarget = torch.rand(8,1,44100)\n\nloss = mrstft(input, target)\n```\n\n# Loss functions\n\nWe categorize the loss functions as either time-domain or frequency-domain approaches. \nAdditionally, we include perceptual transforms.\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Loss functionInterfaceReference
Time domain
Error-to-signal ratio (ESR)auraloss.time.ESRLoss()Wright & Välimäki, 2019
DC error (DC)auraloss.time.DCLoss()Wright & Välimäki, 2019
Log hyperbolic cosine (Log-cosh)auraloss.time.LogCoshLoss()Chen et al., 2019
Signal-to-noise ratio (SNR)auraloss.time.SNRLoss()
Scale-invariant signal-to-distortion
ratio (SI-SDR)		auraloss.time.SISDRLoss()Le Roux et al., 2018
Scale-dependent signal-to-distortion
ratio (SD-SDR)		auraloss.time.SDSDRLoss()Le Roux et al., 2018
Frequency domain
Aggregate STFTauraloss.freq.STFTLoss()Arik et al., 2018
Aggregate Mel-scaled STFTauraloss.freq.MelSTFTLoss(sample_rate)
Multi-resolution STFTauraloss.freq.MultiResolutionSTFTLoss()Yamamoto et al., 2019*
Random-resolution STFTauraloss.freq.RandomResolutionSTFTLoss()Steinmetz & Reiss, 2020
Sum and difference STFT lossauraloss.freq.SumAndDifferenceSTFTLoss()Steinmetz et al., 2020
Perceptual transforms
Sum and difference signal transformauraloss.perceptual.SumAndDifference()
FIR pre-emphasis filtersauraloss.perceptual.FIRFilter()Wright & Välimäki, 2019
\n\n\\* [Wang et al., 2019](https://arxiv.org/abs/1904.12088) also propose a multi-resolution spectral loss (that [Engel et al., 2020](https://arxiv.org/abs/2001.04643) follow), \nbut they do not include both the log magnitude (L1 distance) and spectral convergence terms, introduced in [Arik et al., 2018](https://arxiv.org/abs/1808.0671), and then extended for the multi-resolution case in [Yamamoto et al., 2019](https://arxiv.org/abs/1910.11480).\n\n## Examples\n\nCurrently we include an example using a set of the loss functions to train a TCN for modeling an analog dynamic range compressor. \nFor details please refer to the details in [`examples/compressor`](examples/compressor). \nWe provide pre-trained models, evaluation scripts to compute the metrics in the [paper](https://www.christiansteinmetz.com/s/DMRN15__auraloss__Audio_focused_loss_functions_in_PyTorch.pdf), as well as scripts to retrain models. \n\nThere are some more advanced things you can do based upon the `STFTLoss` class. \nFor example, you can compute both linear and log scaled STFT errors as in [Engel et al., 2020](https://arxiv.org/abs/2001.04643).\nIn this case we do not include the spectral convergence term. \n```python\nstft_loss = auraloss.freq.STFTLoss(w_log_mag=1.0, \n w_lin_mag=1.0, \n w_sc=0.0, )\n```\n\nThere is also a Mel-scaled STFT loss, which has some special requirements. \nThis loss requires you set the sample rate as well as specify the correct device. \n```python\nsample_rate = 44100\nmelstft_loss = auraloss.freq.MelSTFTLoss(sample_rate, device="cuda")\n```\n\nYou can also build a multi-resolution Mel-scaled STFT loss with 64 bins easily. \nMake sure you pass the correct device where the tensors you are comparing will be. \n```python\nmrmelstft_loss = auraloss.freq.MultiResolutionSTFTLoss(scale="mel", \n n_bins=64,\n sample_rate=sample_rate,\n device="cuda")\n```\n\n# Development\n\nWe currently have no tests, but those will also be coming soon, so use caution at the moment. \nFuture loss functions to be included will target neural network based perceptual losses, \nwhich tend to be a bit more sophisticated than those we have included so far. \n\nIf you are interested in adding a loss function please make a pull request. \n\n## Loss functions to be added\n- [Spectral Energy Distance](https://arxiv.org/abs/2008.01160)\n- [TFGAN Losses](https://arxiv.org/abs/2011.12206)\n\n# Cite\nIf you use this code in your work please consider citing us.\n```\n@inproceedings{steinmetz2020auraloss,\n title={auraloss: {A}udio focused loss functions in {PyTorch}},\n author={Steinmetz, Christian J. and Reiss, Joshua D.},\n booktitle={Digital Music Research Network One-day Workshop (DMRN+15)},\n year={2020}}\n```\n'` 2023-01-09T20:12:33,043 According to the spec (see the link below), however, setuptools CANNOT 2023-01-09T20:12:33,044 consider this value unless 'readme' is listed as `dynamic`. 2023-01-09T20:12:33,044 https://packaging.python.org/en/latest/specifications/declaring-project-metadata/ 2023-01-09T20:12:33,045 For the time being, `setuptools` will still consider the given value (as a 2023-01-09T20:12:33,045 **transitional** measure), but please note that future releases of setuptools will 2023-01-09T20:12:33,046 follow strictly the standard. 2023-01-09T20:12:33,046 To prevent this warning, you can list 'readme' under `dynamic` or alternatively 2023-01-09T20:12:33,047 remove the `[project]` table from your file and rely entirely on other means of 2023-01-09T20:12:33,047 configuration. 2023-01-09T20:12:33,048 !! 2023-01-09T20:12:33,049 warnings.warn(msg, _WouldIgnoreField) 2023-01-09T20:12:33,049 /tmp/pip-build-env-4fuq3jq4/overlay/lib/python3.7/site-packages/setuptools/config/_apply_pyprojecttoml.py:103: _WouldIgnoreField: 'requires-python' defined outside of `pyproject.toml` would be ignored. 2023-01-09T20:12:33,049 !! 2023-01-09T20:12:33,050 ########################################################################## 2023-01-09T20:12:33,051 # configuration would be ignored/result in error due to `pyproject.toml` # 2023-01-09T20:12:33,051 ########################################################################## 2023-01-09T20:12:33,052 The following seems to be defined outside of `pyproject.toml`: 2023-01-09T20:12:33,052 `requires-python = '>=3.6.0'` 2023-01-09T20:12:33,053 According to the spec (see the link below), however, setuptools CANNOT 2023-01-09T20:12:33,053 consider this value unless 'requires-python' is listed as `dynamic`. 2023-01-09T20:12:33,054 https://packaging.python.org/en/latest/specifications/declaring-project-metadata/ 2023-01-09T20:12:33,055 For the time being, `setuptools` will still consider the given value (as a 2023-01-09T20:12:33,055 **transitional** measure), but please note that future releases of setuptools will 2023-01-09T20:12:33,055 follow strictly the standard. 2023-01-09T20:12:33,056 To prevent this warning, you can list 'requires-python' under `dynamic` or alternatively 2023-01-09T20:12:33,056 remove the `[project]` table from your file and rely entirely on other means of 2023-01-09T20:12:33,056 configuration. 2023-01-09T20:12:33,057 !! 2023-01-09T20:12:33,058 warnings.warn(msg, _WouldIgnoreField) 2023-01-09T20:12:33,479 running egg_info 2023-01-09T20:12:33,492 writing auraloss.egg-info/PKG-INFO 2023-01-09T20:12:33,497 writing dependency_links to auraloss.egg-info/dependency_links.txt 2023-01-09T20:12:33,502 writing requirements to auraloss.egg-info/requires.txt 2023-01-09T20:12:33,504 writing top-level names to auraloss.egg-info/top_level.txt 2023-01-09T20:12:33,541 reading manifest file 'auraloss.egg-info/SOURCES.txt' 2023-01-09T20:12:33,545 adding license file 'LICENSE' 2023-01-09T20:12:33,550 writing manifest file 'auraloss.egg-info/SOURCES.txt' 2023-01-09T20:12:33,554 /tmp/pip-build-env-4fuq3jq4/overlay/lib/python3.7/site-packages/setuptools/config/_apply_pyprojecttoml.py:103: _WouldIgnoreField: 'license' defined outside of `pyproject.toml` would be ignored. 2023-01-09T20:12:33,554 !! 2023-01-09T20:12:33,555 ########################################################################## 2023-01-09T20:12:33,556 # configuration would be ignored/result in error due to `pyproject.toml` # 2023-01-09T20:12:33,556 ########################################################################## 2023-01-09T20:12:33,557 The following seems to be defined outside of `pyproject.toml`: 2023-01-09T20:12:33,558 `license = 'Apache License 2.0'` 2023-01-09T20:12:33,558 According to the spec (see the link below), however, setuptools CANNOT 2023-01-09T20:12:33,559 consider this value unless 'license' is listed as `dynamic`. 2023-01-09T20:12:33,560 https://packaging.python.org/en/latest/specifications/declaring-project-metadata/ 2023-01-09T20:12:33,561 For the time being, `setuptools` will still consider the given value (as a 2023-01-09T20:12:33,561 **transitional** measure), but please note that future releases of setuptools will 2023-01-09T20:12:33,562 follow strictly the standard. 2023-01-09T20:12:33,563 To prevent this warning, you can list 'license' under `dynamic` or alternatively 2023-01-09T20:12:33,563 remove the `[project]` table from your file and rely entirely on other means of 2023-01-09T20:12:33,564 configuration. 2023-01-09T20:12:33,565 !! 2023-01-09T20:12:33,566 warnings.warn(msg, _WouldIgnoreField) 2023-01-09T20:12:33,566 /tmp/pip-build-env-4fuq3jq4/overlay/lib/python3.7/site-packages/setuptools/config/_apply_pyprojecttoml.py:103: _WouldIgnoreField: 'classifiers' defined outside of `pyproject.toml` would be ignored. 2023-01-09T20:12:33,567 !! 2023-01-09T20:12:33,568 ########################################################################## 2023-01-09T20:12:33,568 # configuration would be ignored/result in error due to `pyproject.toml` # 2023-01-09T20:12:33,569 ########################################################################## 2023-01-09T20:12:33,570 The following seems to be defined outside of `pyproject.toml`: 2023-01-09T20:12:33,570 `classifiers = ['License :: OSI Approved :: Apache Software License', 'Topic :: Multimedia :: Sound/Audio', 'Topic :: Scientific/Engineering']` 2023-01-09T20:12:33,571 According to the spec (see the link below), however, setuptools CANNOT 2023-01-09T20:12:33,572 consider this value unless 'classifiers' is listed as `dynamic`. 2023-01-09T20:12:33,573 https://packaging.python.org/en/latest/specifications/declaring-project-metadata/ 2023-01-09T20:12:33,574 For the time being, `setuptools` will still consider the given value (as a 2023-01-09T20:12:33,574 **transitional** measure), but please note that future releases of setuptools will 2023-01-09T20:12:33,575 follow strictly the standard. 2023-01-09T20:12:33,575 To prevent this warning, you can list 'classifiers' under `dynamic` or alternatively 2023-01-09T20:12:33,576 remove the `[project]` table from your file and rely entirely on other means of 2023-01-09T20:12:33,576 configuration. 2023-01-09T20:12:33,577 !! 2023-01-09T20:12:33,578 warnings.warn(msg, _WouldIgnoreField) 2023-01-09T20:12:33,579 /tmp/pip-build-env-4fuq3jq4/overlay/lib/python3.7/site-packages/setuptools/config/_apply_pyprojecttoml.py:196: UserWarning: `install_requires` overwritten in `pyproject.toml` (dependencies) 2023-01-09T20:12:33,579 warnings.warn(msg) 2023-01-09T20:12:33,788 Getting requirements to build wheel: finished with status 'done' 2023-01-09T20:12:33,809 Created temporary directory: /tmp/pip-modern-metadata-ei6nfbvv 2023-01-09T20:12:33,815 Preparing metadata (pyproject.toml): started 2023-01-09T20:12:33,817 Running command Preparing metadata (pyproject.toml) 2023-01-09T20:12:35,628 /tmp/pip-build-env-4fuq3jq4/overlay/lib/python3.7/site-packages/setuptools/config/_apply_pyprojecttoml.py:103: _WouldIgnoreField: 'readme' defined outside of `pyproject.toml` would be ignored. 2023-01-09T20:12:35,629 !! 2023-01-09T20:12:35,630 ########################################################################## 2023-01-09T20:12:35,631 # configuration would be ignored/result in error due to `pyproject.toml` # 2023-01-09T20:12:35,631 ########################################################################## 2023-01-09T20:12:35,631 The following seems to be defined outside of `pyproject.toml`: 2023-01-09T20:12:35,632 `readme = '\n
\n\n# auraloss\n\n\n\nA collection of audio-focused loss functions in PyTorch. \n\n[[PDF](https://www.christiansteinmetz.com/s/DMRN15__auraloss__Audio_focused_loss_functions_in_PyTorch.pdf)]\n\n
\n\n## Setup\n\n```\npip install auraloss\n```\n\nIf you want to use `MelSTFTLoss()` or `FIRFilter()` you will need to specify the extra install (librosa and scipy).\n\n```\npip install auraloss[all]\n```\n\n## Usage\n\n```python\nimport torch\nimport auraloss\n\nmrstft = auraloss.freq.MultiResolutionSTFTLoss()\n\ninput = torch.rand(8,1,44100)\ntarget = torch.rand(8,1,44100)\n\nloss = mrstft(input, target)\n```\n\n# Loss functions\n\nWe categorize the loss functions as either time-domain or frequency-domain approaches. \nAdditionally, we include perceptual transforms.\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Loss functionInterfaceReference
Time domain
Error-to-signal ratio (ESR)auraloss.time.ESRLoss()Wright & Välimäki, 2019
DC error (DC)auraloss.time.DCLoss()Wright & Välimäki, 2019
Log hyperbolic cosine (Log-cosh)auraloss.time.LogCoshLoss()Chen et al., 2019
Signal-to-noise ratio (SNR)auraloss.time.SNRLoss()
Scale-invariant signal-to-distortion
ratio (SI-SDR)		auraloss.time.SISDRLoss()Le Roux et al., 2018
Scale-dependent signal-to-distortion
ratio (SD-SDR)		auraloss.time.SDSDRLoss()Le Roux et al., 2018
Frequency domain
Aggregate STFTauraloss.freq.STFTLoss()Arik et al., 2018
Aggregate Mel-scaled STFTauraloss.freq.MelSTFTLoss(sample_rate)
Multi-resolution STFTauraloss.freq.MultiResolutionSTFTLoss()Yamamoto et al., 2019*
Random-resolution STFTauraloss.freq.RandomResolutionSTFTLoss()Steinmetz & Reiss, 2020
Sum and difference STFT lossauraloss.freq.SumAndDifferenceSTFTLoss()Steinmetz et al., 2020
Perceptual transforms
Sum and difference signal transformauraloss.perceptual.SumAndDifference()
FIR pre-emphasis filtersauraloss.perceptual.FIRFilter()Wright & Välimäki, 2019
\n\n\\* [Wang et al., 2019](https://arxiv.org/abs/1904.12088) also propose a multi-resolution spectral loss (that [Engel et al., 2020](https://arxiv.org/abs/2001.04643) follow), \nbut they do not include both the log magnitude (L1 distance) and spectral convergence terms, introduced in [Arik et al., 2018](https://arxiv.org/abs/1808.0671), and then extended for the multi-resolution case in [Yamamoto et al., 2019](https://arxiv.org/abs/1910.11480).\n\n## Examples\n\nCurrently we include an example using a set of the loss functions to train a TCN for modeling an analog dynamic range compressor. \nFor details please refer to the details in [`examples/compressor`](examples/compressor). \nWe provide pre-trained models, evaluation scripts to compute the metrics in the [paper](https://www.christiansteinmetz.com/s/DMRN15__auraloss__Audio_focused_loss_functions_in_PyTorch.pdf), as well as scripts to retrain models. \n\nThere are some more advanced things you can do based upon the `STFTLoss` class. \nFor example, you can compute both linear and log scaled STFT errors as in [Engel et al., 2020](https://arxiv.org/abs/2001.04643).\nIn this case we do not include the spectral convergence term. \n```python\nstft_loss = auraloss.freq.STFTLoss(w_log_mag=1.0, \n w_lin_mag=1.0, \n w_sc=0.0, )\n```\n\nThere is also a Mel-scaled STFT loss, which has some special requirements. \nThis loss requires you set the sample rate as well as specify the correct device. \n```python\nsample_rate = 44100\nmelstft_loss = auraloss.freq.MelSTFTLoss(sample_rate, device="cuda")\n```\n\nYou can also build a multi-resolution Mel-scaled STFT loss with 64 bins easily. \nMake sure you pass the correct device where the tensors you are comparing will be. \n```python\nmrmelstft_loss = auraloss.freq.MultiResolutionSTFTLoss(scale="mel", \n n_bins=64,\n sample_rate=sample_rate,\n device="cuda")\n```\n\n# Development\n\nWe currently have no tests, but those will also be coming soon, so use caution at the moment. \nFuture loss functions to be included will target neural network based perceptual losses, \nwhich tend to be a bit more sophisticated than those we have included so far. \n\nIf you are interested in adding a loss function please make a pull request. \n\n## Loss functions to be added\n- [Spectral Energy Distance](https://arxiv.org/abs/2008.01160)\n- [TFGAN Losses](https://arxiv.org/abs/2011.12206)\n\n# Cite\nIf you use this code in your work please consider citing us.\n```\n@inproceedings{steinmetz2020auraloss,\n title={auraloss: {A}udio focused loss functions in {PyTorch}},\n author={Steinmetz, Christian J. and Reiss, Joshua D.},\n booktitle={Digital Music Research Network One-day Workshop (DMRN+15)},\n year={2020}}\n```\n'` 2023-01-09T20:12:35,633 According to the spec (see the link below), however, setuptools CANNOT 2023-01-09T20:12:35,634 consider this value unless 'readme' is listed as `dynamic`. 2023-01-09T20:12:35,634 https://packaging.python.org/en/latest/specifications/declaring-project-metadata/ 2023-01-09T20:12:35,635 For the time being, `setuptools` will still consider the given value (as a 2023-01-09T20:12:35,635 **transitional** measure), but please note that future releases of setuptools will 2023-01-09T20:12:35,636 follow strictly the standard. 2023-01-09T20:12:35,636 To prevent this warning, you can list 'readme' under `dynamic` or alternatively 2023-01-09T20:12:35,636 remove the `[project]` table from your file and rely entirely on other means of 2023-01-09T20:12:35,637 configuration. 2023-01-09T20:12:35,638 !! 2023-01-09T20:12:35,638 warnings.warn(msg, _WouldIgnoreField) 2023-01-09T20:12:35,639 /tmp/pip-build-env-4fuq3jq4/overlay/lib/python3.7/site-packages/setuptools/config/_apply_pyprojecttoml.py:103: _WouldIgnoreField: 'requires-python' defined outside of `pyproject.toml` would be ignored. 2023-01-09T20:12:35,639 !! 2023-01-09T20:12:35,640 ########################################################################## 2023-01-09T20:12:35,640 # configuration would be ignored/result in error due to `pyproject.toml` # 2023-01-09T20:12:35,641 ########################################################################## 2023-01-09T20:12:35,641 The following seems to be defined outside of `pyproject.toml`: 2023-01-09T20:12:35,642 `requires-python = '>=3.6.0'` 2023-01-09T20:12:35,643 According to the spec (see the link below), however, setuptools CANNOT 2023-01-09T20:12:35,643 consider this value unless 'requires-python' is listed as `dynamic`. 2023-01-09T20:12:35,644 https://packaging.python.org/en/latest/specifications/declaring-project-metadata/ 2023-01-09T20:12:35,644 For the time being, `setuptools` will still consider the given value (as a 2023-01-09T20:12:35,645 **transitional** measure), but please note that future releases of setuptools will 2023-01-09T20:12:35,645 follow strictly the standard. 2023-01-09T20:12:35,646 To prevent this warning, you can list 'requires-python' under `dynamic` or alternatively 2023-01-09T20:12:35,646 remove the `[project]` table from your file and rely entirely on other means of 2023-01-09T20:12:35,646 configuration. 2023-01-09T20:12:35,647 !! 2023-01-09T20:12:35,648 warnings.warn(msg, _WouldIgnoreField) 2023-01-09T20:12:36,039 running dist_info 2023-01-09T20:12:36,054 creating /tmp/pip-modern-metadata-ei6nfbvv/auraloss.egg-info 2023-01-09T20:12:36,065 writing /tmp/pip-modern-metadata-ei6nfbvv/auraloss.egg-info/PKG-INFO 2023-01-09T20:12:36,070 writing dependency_links to /tmp/pip-modern-metadata-ei6nfbvv/auraloss.egg-info/dependency_links.txt 2023-01-09T20:12:36,075 writing requirements to /tmp/pip-modern-metadata-ei6nfbvv/auraloss.egg-info/requires.txt 2023-01-09T20:12:36,077 writing top-level names to /tmp/pip-modern-metadata-ei6nfbvv/auraloss.egg-info/top_level.txt 2023-01-09T20:12:36,080 writing manifest file '/tmp/pip-modern-metadata-ei6nfbvv/auraloss.egg-info/SOURCES.txt' 2023-01-09T20:12:36,112 reading manifest file '/tmp/pip-modern-metadata-ei6nfbvv/auraloss.egg-info/SOURCES.txt' 2023-01-09T20:12:36,119 adding license file 'LICENSE' 2023-01-09T20:12:36,124 writing manifest file '/tmp/pip-modern-metadata-ei6nfbvv/auraloss.egg-info/SOURCES.txt' 2023-01-09T20:12:36,126 creating '/tmp/pip-modern-metadata-ei6nfbvv/auraloss-0.3.0.dist-info' 2023-01-09T20:12:36,210 /tmp/pip-build-env-4fuq3jq4/overlay/lib/python3.7/site-packages/setuptools/config/_apply_pyprojecttoml.py:103: _WouldIgnoreField: 'license' defined outside of `pyproject.toml` would be ignored. 2023-01-09T20:12:36,210 !! 2023-01-09T20:12:36,211 ########################################################################## 2023-01-09T20:12:36,212 # configuration would be ignored/result in error due to `pyproject.toml` # 2023-01-09T20:12:36,212 ########################################################################## 2023-01-09T20:12:36,213 The following seems to be defined outside of `pyproject.toml`: 2023-01-09T20:12:36,214 `license = 'Apache License 2.0'` 2023-01-09T20:12:36,215 According to the spec (see the link below), however, setuptools CANNOT 2023-01-09T20:12:36,215 consider this value unless 'license' is listed as `dynamic`. 2023-01-09T20:12:36,216 https://packaging.python.org/en/latest/specifications/declaring-project-metadata/ 2023-01-09T20:12:36,217 For the time being, `setuptools` will still consider the given value (as a 2023-01-09T20:12:36,217 **transitional** measure), but please note that future releases of setuptools will 2023-01-09T20:12:36,218 follow strictly the standard. 2023-01-09T20:12:36,219 To prevent this warning, you can list 'license' under `dynamic` or alternatively 2023-01-09T20:12:36,219 remove the `[project]` table from your file and rely entirely on other means of 2023-01-09T20:12:36,220 configuration. 2023-01-09T20:12:36,221 !! 2023-01-09T20:12:36,222 warnings.warn(msg, _WouldIgnoreField) 2023-01-09T20:12:36,222 /tmp/pip-build-env-4fuq3jq4/overlay/lib/python3.7/site-packages/setuptools/config/_apply_pyprojecttoml.py:103: _WouldIgnoreField: 'classifiers' defined outside of `pyproject.toml` would be ignored. 2023-01-09T20:12:36,223 !! 2023-01-09T20:12:36,224 ########################################################################## 2023-01-09T20:12:36,225 # configuration would be ignored/result in error due to `pyproject.toml` # 2023-01-09T20:12:36,225 ########################################################################## 2023-01-09T20:12:36,226 The following seems to be defined outside of `pyproject.toml`: 2023-01-09T20:12:36,227 `classifiers = ['License :: OSI Approved :: Apache Software License', 'Topic :: Multimedia :: Sound/Audio', 'Topic :: Scientific/Engineering']` 2023-01-09T20:12:36,228 According to the spec (see the link below), however, setuptools CANNOT 2023-01-09T20:12:36,228 consider this value unless 'classifiers' is listed as `dynamic`. 2023-01-09T20:12:36,229 https://packaging.python.org/en/latest/specifications/declaring-project-metadata/ 2023-01-09T20:12:36,230 For the time being, `setuptools` will still consider the given value (as a 2023-01-09T20:12:36,230 **transitional** measure), but please note that future releases of setuptools will 2023-01-09T20:12:36,231 follow strictly the standard. 2023-01-09T20:12:36,231 To prevent this warning, you can list 'classifiers' under `dynamic` or alternatively 2023-01-09T20:12:36,232 remove the `[project]` table from your file and rely entirely on other means of 2023-01-09T20:12:36,232 configuration. 2023-01-09T20:12:36,233 !! 2023-01-09T20:12:36,234 warnings.warn(msg, _WouldIgnoreField) 2023-01-09T20:12:36,235 /tmp/pip-build-env-4fuq3jq4/overlay/lib/python3.7/site-packages/setuptools/config/_apply_pyprojecttoml.py:196: UserWarning: `install_requires` overwritten in `pyproject.toml` (dependencies) 2023-01-09T20:12:36,235 warnings.warn(msg) 2023-01-09T20:12:36,446 Preparing metadata (pyproject.toml): finished with status 'done' 2023-01-09T20:12:36,462 Source in /tmp/pip-wheel-uvgw5fyc/auraloss_533dff4aa4ec4e4a9d5546f977c4729e has version 0.3.0, which satisfies requirement auraloss==0.3.0 from https://files.pythonhosted.org/packages/1e/6e/0b8c140e51450b9f558bf9483500989d9b81e0bc99073b38743cb6739a15/auraloss-0.3.0.tar.gz 2023-01-09T20:12:36,464 Removed auraloss==0.3.0 from https://files.pythonhosted.org/packages/1e/6e/0b8c140e51450b9f558bf9483500989d9b81e0bc99073b38743cb6739a15/auraloss-0.3.0.tar.gz from build tracker '/tmp/pip-build-tracker-60izmwaz' 2023-01-09T20:12:36,478 Created temporary directory: /tmp/pip-unpack-l03k660l 2023-01-09T20:12:36,479 Building wheels for collected packages: auraloss 2023-01-09T20:12:36,489 Created temporary directory: /tmp/pip-wheel-l2t_10lr 2023-01-09T20:12:36,490 Destination directory: /tmp/pip-wheel-l2t_10lr 2023-01-09T20:12:36,495 Building wheel for auraloss (pyproject.toml): started 2023-01-09T20:12:36,498 Running command Building wheel for auraloss (pyproject.toml) 2023-01-09T20:12:38,268 /tmp/pip-build-env-4fuq3jq4/overlay/lib/python3.7/site-packages/setuptools/config/_apply_pyprojecttoml.py:103: _WouldIgnoreField: 'readme' defined outside of `pyproject.toml` would be ignored. 2023-01-09T20:12:38,270 !! 2023-01-09T20:12:38,271 ########################################################################## 2023-01-09T20:12:38,271 # configuration would be ignored/result in error due to `pyproject.toml` # 2023-01-09T20:12:38,271 ########################################################################## 2023-01-09T20:12:38,272 The following seems to be defined outside of `pyproject.toml`: 2023-01-09T20:12:38,273 `readme = '\n
\n\n# auraloss\n\n\n\nA collection of audio-focused loss functions in PyTorch. \n\n[[PDF](https://www.christiansteinmetz.com/s/DMRN15__auraloss__Audio_focused_loss_functions_in_PyTorch.pdf)]\n\n
\n\n## Setup\n\n```\npip install auraloss\n```\n\nIf you want to use `MelSTFTLoss()` or `FIRFilter()` you will need to specify the extra install (librosa and scipy).\n\n```\npip install auraloss[all]\n```\n\n## Usage\n\n```python\nimport torch\nimport auraloss\n\nmrstft = auraloss.freq.MultiResolutionSTFTLoss()\n\ninput = torch.rand(8,1,44100)\ntarget = torch.rand(8,1,44100)\n\nloss = mrstft(input, target)\n```\n\n# Loss functions\n\nWe categorize the loss functions as either time-domain or frequency-domain approaches. \nAdditionally, we include perceptual transforms.\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Loss functionInterfaceReference
Time domain
Error-to-signal ratio (ESR)auraloss.time.ESRLoss()Wright & Välimäki, 2019
DC error (DC)auraloss.time.DCLoss()Wright & Välimäki, 2019
Log hyperbolic cosine (Log-cosh)auraloss.time.LogCoshLoss()Chen et al., 2019
Signal-to-noise ratio (SNR)auraloss.time.SNRLoss()
Scale-invariant signal-to-distortion
ratio (SI-SDR)		auraloss.time.SISDRLoss()Le Roux et al., 2018
Scale-dependent signal-to-distortion
ratio (SD-SDR)		auraloss.time.SDSDRLoss()Le Roux et al., 2018
Frequency domain
Aggregate STFTauraloss.freq.STFTLoss()Arik et al., 2018
Aggregate Mel-scaled STFTauraloss.freq.MelSTFTLoss(sample_rate)
Multi-resolution STFTauraloss.freq.MultiResolutionSTFTLoss()Yamamoto et al., 2019*
Random-resolution STFTauraloss.freq.RandomResolutionSTFTLoss()Steinmetz & Reiss, 2020
Sum and difference STFT lossauraloss.freq.SumAndDifferenceSTFTLoss()Steinmetz et al., 2020
Perceptual transforms
Sum and difference signal transformauraloss.perceptual.SumAndDifference()
FIR pre-emphasis filtersauraloss.perceptual.FIRFilter()Wright & Välimäki, 2019
\n\n\\* [Wang et al., 2019](https://arxiv.org/abs/1904.12088) also propose a multi-resolution spectral loss (that [Engel et al., 2020](https://arxiv.org/abs/2001.04643) follow), \nbut they do not include both the log magnitude (L1 distance) and spectral convergence terms, introduced in [Arik et al., 2018](https://arxiv.org/abs/1808.0671), and then extended for the multi-resolution case in [Yamamoto et al., 2019](https://arxiv.org/abs/1910.11480).\n\n## Examples\n\nCurrently we include an example using a set of the loss functions to train a TCN for modeling an analog dynamic range compressor. \nFor details please refer to the details in [`examples/compressor`](examples/compressor). \nWe provide pre-trained models, evaluation scripts to compute the metrics in the [paper](https://www.christiansteinmetz.com/s/DMRN15__auraloss__Audio_focused_loss_functions_in_PyTorch.pdf), as well as scripts to retrain models. \n\nThere are some more advanced things you can do based upon the `STFTLoss` class. \nFor example, you can compute both linear and log scaled STFT errors as in [Engel et al., 2020](https://arxiv.org/abs/2001.04643).\nIn this case we do not include the spectral convergence term. \n```python\nstft_loss = auraloss.freq.STFTLoss(w_log_mag=1.0, \n w_lin_mag=1.0, \n w_sc=0.0, )\n```\n\nThere is also a Mel-scaled STFT loss, which has some special requirements. \nThis loss requires you set the sample rate as well as specify the correct device. \n```python\nsample_rate = 44100\nmelstft_loss = auraloss.freq.MelSTFTLoss(sample_rate, device="cuda")\n```\n\nYou can also build a multi-resolution Mel-scaled STFT loss with 64 bins easily. \nMake sure you pass the correct device where the tensors you are comparing will be. \n```python\nmrmelstft_loss = auraloss.freq.MultiResolutionSTFTLoss(scale="mel", \n n_bins=64,\n sample_rate=sample_rate,\n device="cuda")\n```\n\n# Development\n\nWe currently have no tests, but those will also be coming soon, so use caution at the moment. \nFuture loss functions to be included will target neural network based perceptual losses, \nwhich tend to be a bit more sophisticated than those we have included so far. \n\nIf you are interested in adding a loss function please make a pull request. \n\n## Loss functions to be added\n- [Spectral Energy Distance](https://arxiv.org/abs/2008.01160)\n- [TFGAN Losses](https://arxiv.org/abs/2011.12206)\n\n# Cite\nIf you use this code in your work please consider citing us.\n```\n@inproceedings{steinmetz2020auraloss,\n title={auraloss: {A}udio focused loss functions in {PyTorch}},\n author={Steinmetz, Christian J. and Reiss, Joshua D.},\n booktitle={Digital Music Research Network One-day Workshop (DMRN+15)},\n year={2020}}\n```\n'` 2023-01-09T20:12:38,274 According to the spec (see the link below), however, setuptools CANNOT 2023-01-09T20:12:38,274 consider this value unless 'readme' is listed as `dynamic`. 2023-01-09T20:12:38,275 https://packaging.python.org/en/latest/specifications/declaring-project-metadata/ 2023-01-09T20:12:38,275 For the time being, `setuptools` will still consider the given value (as a 2023-01-09T20:12:38,276 **transitional** measure), but please note that future releases of setuptools will 2023-01-09T20:12:38,276 follow strictly the standard. 2023-01-09T20:12:38,277 To prevent this warning, you can list 'readme' under `dynamic` or alternatively 2023-01-09T20:12:38,277 remove the `[project]` table from your file and rely entirely on other means of 2023-01-09T20:12:38,277 configuration. 2023-01-09T20:12:38,278 !! 2023-01-09T20:12:38,279 warnings.warn(msg, _WouldIgnoreField) 2023-01-09T20:12:38,279 /tmp/pip-build-env-4fuq3jq4/overlay/lib/python3.7/site-packages/setuptools/config/_apply_pyprojecttoml.py:103: _WouldIgnoreField: 'requires-python' defined outside of `pyproject.toml` would be ignored. 2023-01-09T20:12:38,280 !! 2023-01-09T20:12:38,281 ########################################################################## 2023-01-09T20:12:38,281 # configuration would be ignored/result in error due to `pyproject.toml` # 2023-01-09T20:12:38,281 ########################################################################## 2023-01-09T20:12:38,282 The following seems to be defined outside of `pyproject.toml`: 2023-01-09T20:12:38,282 `requires-python = '>=3.6.0'` 2023-01-09T20:12:38,283 According to the spec (see the link below), however, setuptools CANNOT 2023-01-09T20:12:38,283 consider this value unless 'requires-python' is listed as `dynamic`. 2023-01-09T20:12:38,284 https://packaging.python.org/en/latest/specifications/declaring-project-metadata/ 2023-01-09T20:12:38,285 For the time being, `setuptools` will still consider the given value (as a 2023-01-09T20:12:38,285 **transitional** measure), but please note that future releases of setuptools will 2023-01-09T20:12:38,285 follow strictly the standard. 2023-01-09T20:12:38,286 To prevent this warning, you can list 'requires-python' under `dynamic` or alternatively 2023-01-09T20:12:38,286 remove the `[project]` table from your file and rely entirely on other means of 2023-01-09T20:12:38,287 configuration. 2023-01-09T20:12:38,288 !! 2023-01-09T20:12:38,288 warnings.warn(msg, _WouldIgnoreField) 2023-01-09T20:12:38,668 running bdist_wheel 2023-01-09T20:12:38,702 running build 2023-01-09T20:12:38,702 running build_py 2023-01-09T20:12:38,714 creating build 2023-01-09T20:12:38,715 creating build/lib 2023-01-09T20:12:38,716 creating build/lib/auraloss 2023-01-09T20:12:38,718 copying auraloss/__init__.py -> build/lib/auraloss 2023-01-09T20:12:38,722 copying auraloss/plotting.py -> build/lib/auraloss 2023-01-09T20:12:38,725 copying auraloss/freq.py -> build/lib/auraloss 2023-01-09T20:12:38,730 copying auraloss/time.py -> build/lib/auraloss 2023-01-09T20:12:38,734 copying auraloss/utils.py -> build/lib/auraloss 2023-01-09T20:12:38,737 copying auraloss/perceptual.py -> build/lib/auraloss 2023-01-09T20:12:38,740 running egg_info 2023-01-09T20:12:38,761 writing auraloss.egg-info/PKG-INFO 2023-01-09T20:12:38,765 writing dependency_links to auraloss.egg-info/dependency_links.txt 2023-01-09T20:12:38,768 writing requirements to auraloss.egg-info/requires.txt 2023-01-09T20:12:38,770 writing top-level names to auraloss.egg-info/top_level.txt 2023-01-09T20:12:38,786 reading manifest file 'auraloss.egg-info/SOURCES.txt' 2023-01-09T20:12:38,789 adding license file 'LICENSE' 2023-01-09T20:12:38,795 writing manifest file 'auraloss.egg-info/SOURCES.txt' 2023-01-09T20:12:38,816 installing to build/bdist.linux-armv7l/wheel 2023-01-09T20:12:38,817 running install 2023-01-09T20:12:38,880 running install_lib 2023-01-09T20:12:38,891 creating build/bdist.linux-armv7l 2023-01-09T20:12:38,892 creating build/bdist.linux-armv7l/wheel 2023-01-09T20:12:38,895 creating build/bdist.linux-armv7l/wheel/auraloss 2023-01-09T20:12:38,897 copying build/lib/auraloss/__init__.py -> build/bdist.linux-armv7l/wheel/auraloss 2023-01-09T20:12:38,901 copying build/lib/auraloss/plotting.py -> build/bdist.linux-armv7l/wheel/auraloss 2023-01-09T20:12:38,904 copying build/lib/auraloss/freq.py -> build/bdist.linux-armv7l/wheel/auraloss 2023-01-09T20:12:38,909 copying build/lib/auraloss/time.py -> build/bdist.linux-armv7l/wheel/auraloss 2023-01-09T20:12:38,914 copying build/lib/auraloss/utils.py -> build/bdist.linux-armv7l/wheel/auraloss 2023-01-09T20:12:38,918 copying build/lib/auraloss/perceptual.py -> build/bdist.linux-armv7l/wheel/auraloss 2023-01-09T20:12:38,921 running install_egg_info 2023-01-09T20:12:38,931 Copying auraloss.egg-info to build/bdist.linux-armv7l/wheel/auraloss-0.3.0-py3.7.egg-info 2023-01-09T20:12:38,951 running install_scripts 2023-01-09T20:12:38,995 creating build/bdist.linux-armv7l/wheel/auraloss-0.3.0.dist-info/WHEEL 2023-01-09T20:12:39,001 creating '/tmp/pip-wheel-l2t_10lr/.tmp-kppvk9or/auraloss-0.3.0-py3-none-any.whl' and adding 'build/bdist.linux-armv7l/wheel' to it 2023-01-09T20:12:39,006 adding 'auraloss/__init__.py' 2023-01-09T20:12:39,011 adding 'auraloss/freq.py' 2023-01-09T20:12:39,015 adding 'auraloss/perceptual.py' 2023-01-09T20:12:39,017 adding 'auraloss/plotting.py' 2023-01-09T20:12:39,020 adding 'auraloss/time.py' 2023-01-09T20:12:39,023 adding 'auraloss/utils.py' 2023-01-09T20:12:39,030 adding 'auraloss-0.3.0.dist-info/LICENSE' 2023-01-09T20:12:39,033 adding 'auraloss-0.3.0.dist-info/METADATA' 2023-01-09T20:12:39,035 adding 'auraloss-0.3.0.dist-info/WHEEL' 2023-01-09T20:12:39,037 adding 'auraloss-0.3.0.dist-info/top_level.txt' 2023-01-09T20:12:39,039 adding 'auraloss-0.3.0.dist-info/RECORD' 2023-01-09T20:12:39,041 removing build/bdist.linux-armv7l/wheel 2023-01-09T20:12:39,054 /tmp/pip-build-env-4fuq3jq4/overlay/lib/python3.7/site-packages/setuptools/config/_apply_pyprojecttoml.py:103: _WouldIgnoreField: 'license' defined outside of `pyproject.toml` would be ignored. 2023-01-09T20:12:39,054 !! 2023-01-09T20:12:39,055 ########################################################################## 2023-01-09T20:12:39,056 # configuration would be ignored/result in error due to `pyproject.toml` # 2023-01-09T20:12:39,056 ########################################################################## 2023-01-09T20:12:39,057 The following seems to be defined outside of `pyproject.toml`: 2023-01-09T20:12:39,058 `license = 'Apache License 2.0'` 2023-01-09T20:12:39,059 According to the spec (see the link below), however, setuptools CANNOT 2023-01-09T20:12:39,059 consider this value unless 'license' is listed as `dynamic`. 2023-01-09T20:12:39,060 https://packaging.python.org/en/latest/specifications/declaring-project-metadata/ 2023-01-09T20:12:39,061 For the time being, `setuptools` will still consider the given value (as a 2023-01-09T20:12:39,061 **transitional** measure), but please note that future releases of setuptools will 2023-01-09T20:12:39,062 follow strictly the standard. 2023-01-09T20:12:39,063 To prevent this warning, you can list 'license' under `dynamic` or alternatively 2023-01-09T20:12:39,064 remove the `[project]` table from your file and rely entirely on other means of 2023-01-09T20:12:39,064 configuration. 2023-01-09T20:12:39,065 !! 2023-01-09T20:12:39,066 warnings.warn(msg, _WouldIgnoreField) 2023-01-09T20:12:39,067 /tmp/pip-build-env-4fuq3jq4/overlay/lib/python3.7/site-packages/setuptools/config/_apply_pyprojecttoml.py:103: _WouldIgnoreField: 'classifiers' defined outside of `pyproject.toml` would be ignored. 2023-01-09T20:12:39,067 !! 2023-01-09T20:12:39,068 ########################################################################## 2023-01-09T20:12:39,069 # configuration would be ignored/result in error due to `pyproject.toml` # 2023-01-09T20:12:39,069 ########################################################################## 2023-01-09T20:12:39,070 The following seems to be defined outside of `pyproject.toml`: 2023-01-09T20:12:39,071 `classifiers = ['License :: OSI Approved :: Apache Software License', 'Topic :: Multimedia :: Sound/Audio', 'Topic :: Scientific/Engineering']` 2023-01-09T20:12:39,072 According to the spec (see the link below), however, setuptools CANNOT 2023-01-09T20:12:39,073 consider this value unless 'classifiers' is listed as `dynamic`. 2023-01-09T20:12:39,074 https://packaging.python.org/en/latest/specifications/declaring-project-metadata/ 2023-01-09T20:12:39,075 For the time being, `setuptools` will still consider the given value (as a 2023-01-09T20:12:39,075 **transitional** measure), but please note that future releases of setuptools will 2023-01-09T20:12:39,075 follow strictly the standard. 2023-01-09T20:12:39,076 To prevent this warning, you can list 'classifiers' under `dynamic` or alternatively 2023-01-09T20:12:39,077 remove the `[project]` table from your file and rely entirely on other means of 2023-01-09T20:12:39,077 configuration. 2023-01-09T20:12:39,078 !! 2023-01-09T20:12:39,079 warnings.warn(msg, _WouldIgnoreField) 2023-01-09T20:12:39,080 /tmp/pip-build-env-4fuq3jq4/overlay/lib/python3.7/site-packages/setuptools/config/_apply_pyprojecttoml.py:196: UserWarning: `install_requires` overwritten in `pyproject.toml` (dependencies) 2023-01-09T20:12:39,080 warnings.warn(msg) 2023-01-09T20:12:39,291 Building wheel for auraloss (pyproject.toml): finished with status 'done' 2023-01-09T20:12:39,303 Created wheel for auraloss: filename=auraloss-0.3.0-py3-none-any.whl size=15795 sha256=0de12183d93ed3a210e80b31da45736da1866ae97d3f6f275c25364f793f6dd1 2023-01-09T20:12:39,305 Stored in directory: /tmp/pip-ephem-wheel-cache-ex5zfchb/wheels/1f/d1/7d/a3c70c7ab085b9c8fe2718e6b7e218e1d4ae8894cc90a2b533 2023-01-09T20:12:39,332 Successfully built auraloss 2023-01-09T20:12:39,340 Removed build tracker: '/tmp/pip-build-tracker-60izmwaz'