Change log

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>

• #12: [experimental] Add nnmnkwii.metrics package
• #42: Fix installation failsure on no-utf-8 environments

v0.0.6 <2017-10-01>

• #38: Add parameter trajectory smoothing.
• #37: Add tqdm as dependency. Dataset’s asarray now report progress if verbose > 0.
• #37: Add further support for incremental mean/var computation.
• #37: Add and improve normalization utilities, nnmnkwii.preprocessing.inv_scale(), nnmnkwii.preprocessing.inv_minmax_scale() and nnmnkwii.preprocessing.minmax_scale_params().
• Add builtin data source for Voice Conversion Challenge (VCC) 2016 dataset.
• #34: Add nnmnkwii.preprocessing.adjast_frame_length().
• #34: adjast_frame_lengths now supports divisible_by parameter. ensure_even is deprecated.
• #34: Rename adjast_frame_length to adjast_Frame_lengths
• Add references to nnmnkwii.postfilters.merlin_post_filter().

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>

• Add tests, achieve 75% test coverage.
• #23, #22: Preprocess rewrite & module restructure.
• #21: Add new function nnmnkwii.autograd.UnitVarianceMLPG that can run on CPU/GPU.

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