nnmnkwii
Library to build speech synthesis systems designed for easy and fast prototyping.
OTHER License
What's Changed
- Bump numpy requirement to >=v1.20.0 by @r9y9 in https://github.com/r9y9/nnmnkwii/pull/123
- prep for new release by @r9y9 in https://github.com/r9y9/nnmnkwii/pull/125
Full Changelog: https://github.com/r9y9/nnmnkwii/compare/v0.1.1...v0.1.2
Published by r9y9 almost 3 years ago
v0.1.1 <2021-01-04>
- #120: Revise CI: Enable windows and mac osx CI with Github actions. AppVeyor is removed instead.
- #118: Fixes ValueError("Newlines are not allowed") at installation time
Published by r9y9 about 3 years ago
- #114: Use pysen for linting/formatting
- Removed display package
- Fix hts.load when the input label is empty
- Add hts.io.HTSLabelFile.create_from_contexts
- Fix build time numpy requirement to <v1.20.0
- Support for loading HTS-style labels with time unit in seconds
Published by r9y9 over 3 years ago
v0.0.23 <2021-05-15>
-
#112_: Renamed continuous_dict to numeric_dict to be more precise. -
#112_: Bandmat is now a part of nnmnkwii's internal package. This is to avoid instllation failusres on python >=3.6. https://github.com/MattShannon/bandmat/issues/10 -
#112_: Started testing using github actions (python 3.7, 3.8, 3.9) -
#112_: [hts.io]: :func:nnmnkwii.io.hts.load_question_setnow keeps question names (e.g. "L-Phone_Boin") in dictionary. -
#112_: [hts.io]: New functionality :func:nnmnkwii.io.hts.write_audacity_labels -
#112_: [hts.io]: New functionality :func:nnmnkwii.io.hts.write_textgrid -
#112_: Renamed np.int to int -
#112_: Added pyproject.yaml
Published by r9y9 almost 4 years ago
v0.0.22 <2020-12-25>
- #105: Change sklearn to scikit-learn
- #108: Fix label time overflow on environment which size of np.int is 4bytes
- #109: io: fix bug of handling pitch diff in the SVS full context format
- io: allow writing comments in hed files
Published by r9y9 about 4 years ago
v0.0.21 <2020-08-13>
- #99: Fix future warning from sklearn
- #101: [hts][frontend] various fixes for singing voice synthesis. Our frontend now supports MIDI number extraction. HTSLabelFile supports list and slice indexing.
Published by r9y9 over 4 years ago
v0.0.20 <2020-03-02>
- #90: Expand available speakers list for CMU Arctic dataset
- #91: Add support for JVS dataset: a free Japanese multi-speaker voice corpus.
- #98: Enable python 3.8 tests on travis
- #95: Fixed parameter generation error of MLPG.
Published by r9y9 over 5 years ago
Published by r9y9 over 5 years ago
Published by r9y9 almost 6 years ago
Merry Christmas!
Summary of changes
- autograd: Compat fixes for pytorch v1.0.0 https://github.com/r9y9/nnmnkwii/pull/79, https://github.com/r9y9/nnmnkwii/pull/76
- New logo https://github.com/r9y9/nnmnkwii/pull/78
Published by r9y9 about 6 years ago
