Skip to content

Releases: crlandsc/torch-log-wmse

v0.2.9

31 Jul 18:06
Compare
Choose a tag to compare

What's Changed

  • Added bypass_filter argument that will bypass frequency weighting if True.
  • Add RMS_EPS in divisor to avoid NaN by @iver56 in #3

New Contributors

  • @iver56 made their first contribution in #3

Full Changelog: v0.2.7...v0.2.9

v0.2.7

21 Jun 20:21
Compare
Choose a tag to compare

Added alias file so imports can either be torch_log_wmse or torch_log_wmse_audio_quality (for legacy use).
Full Changelog: v0.2.3...v0.2.7

v0.2.3

19 Jun 15:11
Compare
Choose a tag to compare

Corrected file reference to pkl filter file.
Full Changelog: v0.2.2...v0.2.3

v0.2.2

18 Jun 18:14
Compare
Choose a tag to compare

Changed GitHub repo name & references

Updated GitHub repo name to appropriate torch-log-wmse. torch-log-wmse-audio-quality can still be installed, but everything will reference the new name (torch-log-wmse) moving forward.

Full Changelog: v0.2.1...v0.2.2

v0.2.1

18 Jun 17:53
Compare
Choose a tag to compare

Package Name Change

  • Added pip package torch-log-wmse. Now the package can be installed as either torch-log-wmse or torch-log-wmse-audio-quality.
  • Changed name of imports to torch_log_wmse independent of installation name (i.e. pip install torch-log-wmse or pip install torch-log-wmse-audio-quality). Imports now MUST be done as the following:
from torch_log_wmse import LogWMSE

Full Changelog: v0.1.8...v0.2.1

v0.1.8

22 May 23:28
Compare
Choose a tag to compare

Changed scaling factor so RMS doesn't need to = 0, rather just be lower than the error threshold to replace with min value. If it only could be 0, then very tiny numbers even closer to 0 would still go through.

Full Changelog: v0.1.7...v0.1.8

v0.1.7

22 May 21:26
Compare
Choose a tag to compare

If the unprocessed audio was silent, a value was immediately being returned unrelated to the model predictions. While this is how the original metric was implemented here, the RMS value should actually be replaced with epsilon so that the difference between a non-silent output and silent output can be measured.

Added test for silent input & target.

Adjusted circular shift to account for IR with odd number of samples.

Full Changelog: v0.1.6...v0.1.7

v0.1.6

20 May 21:50
Compare
Choose a tag to compare

Full Changelog: v0.1.5...v0.1.6

v0.1.5

17 May 19:11
Compare
Choose a tag to compare

Full Changelog: v0.1.4...v0.1.5

v0.1.4

17 May 17:31
Compare
Choose a tag to compare

Initial GitHub release to sync with PyPI.

Full Changelog: https://github.com/crlandsc/torch-log-wmse-audio-quality/commits/v0.1.4