Change log

v0.1.0 <2021-08-11>

  • #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

v0.0.23 <2021-05-15>

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

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.

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.


v0.0.19 <2019-07-06>

v0.0.18 <2019-05-31>

  • Fix for python 3.7.

v0.0.17 <2018-12-25>

  • #79: ModSpec update for Pytorch 1.0.0. Fix deprecations.

  • #40: Add logo

  • #76: MLPG update for PyTorch 1.0.0.

v0.0.16 <2018-08-23>

  • #73: Add Japanese TTS demo to docs and fix some typos.

  • #72: Add TranscriptionDataSource for VoiceStatistics (ja) dataset

  • #72: Deprecate NormalizedTranscriptionDataSource for LJSpeech dataset.

  • hts.load now accepts lines argment.

v0.0.15 <2018-07-12>

  • Fix pypi release to render markdown property

v0.0.14 <2018-06-06>

  • #67: Windows support (experimental)

  • #66: Fixed window installation issue

  • #71: Bump bandmat version to v0.7

v0.0.13 <2018-01-24>

  • #65: Part of example data was not installed by setuptools. Fixed.

  • #63: Windows CI

v0.0.12 <2018-01-04>

  • Fix typo: adjast_frame_length and adjast_frame_lengths are renamed to adjust_frame_length and adjust_frame_lengths, respectively,

  • #63: Improved support for nnmnkwii.preprocessing.adjast_frame_length() and nnmnkwii.preprocessing.adjast_frame_lengths(). Padding for 1d array is now supported.

  • BUG FIX: example audio data is now included in the release tar.gz

v0.0.11 <2017-12-22>

  • Fix RuntimeError when HTS label file has white spaces between fields. Skip comments when reading HTS labels.

v0.0.10 <2017-12-05>

  • #61: Misc dataset improvements. Unified max_files=None from max_files=50 and add max_files args for VCTK data sources.

  • #59: Bug fix for memory re-allocations when num frames exceed padded_initial_guess

  • #60: FileSourceDataset: better descriptive error messages

  • #57: Add append method to HTSLabelFile and simplify structure. frame_shift_in_micro_sec was removed from its property.

  • #55: Add mu-law companding/expansion

  • Add support for JSUT dataset ver 1.1

  • #20: Support for mono phone labels and fix bug of silence_phone_indices() for non-state level alignment label files.

v0.0.9 <2017-11-14>

  • #53: Add builtin data sources for VCTK dataset

  • #50: Add builtin data sources for JSUT dataset

  • #51: Fix modspec autograd bug for norm='ortho'

v0.0.8 <2017-10-25>

  • #49: Add support for build without cython

  • #46: Cleanup frontnend implementation

v0.0.7 <2017-10-09>

v0.0.6 <2017-10-01>

v0.0.5 <2017-09-19>

  • #19: Achieved 80% test coverage

  • #31: Cleanup data source implementations and add docs.

  • Fix example data wasn’t included in release tar ball.

  • Support padded_length is None for nnmnkwii.datasets.FileSourceDataset.

  • Automatic frame length adjastment for DTWAligner / IterativeDTWAligner

v0.0.4 <2017-09-01>

  • #28: Setuptools improvements. 1) __version__ now includes git commit hash. 2) description read README.rst using pandoc.

  • #27: Add preemphasis / inv_preemphasis

  • #26: Add tests for GMM based voice conversion if swap=True

  • #25: fix typo in nnmnkwii/baseline/gmm.py

v0.0.3 <2017-08-26>

v0.0.2 <2017-08-18>

  • hts io: Add support for full-context only label files

  • #17: ts io: Fix wildcard handling bug

  • Use pack_pad_sequence for RNN training and add tests for this

  • Faster MLPG gradient computation

v0.0.1 <2017-08-14>

  • Initial release