A python wrapper for OpenJTalk.
The package consists of two core components:
- Text processing frontend based on OpenJTalk
- Speech synthesis backend using HTSEngine
- The package is built with the modified version of OpenJTalk. The modified version provides the same functionality with some improvements (e.g., cmake support) but is technically different from the one from HTS working group.
- The package also uses the modified version of hts_engine_API. The same applies as above.
Before using the pyopenjtalk package, please have a look at the LICENSE for the two software.
The python package relies on cython to make python bindings for open_jtalk and hts_engine_API. You must need the following tools to build and install pyopenjtalk:
- C/C++ compilers (to build C/C++ extentions)
- cmake
- cython
- Linux
- Mac OSX
- Windows (MSVC) (see this PR)
pip install pyopenjtalk
To build the package locally, you will need to make sure to clone open_jtalk and hts_engine_API.
git submodule update --recursive --init
and then run
pip install -e .
Please check the notebook version here (nbviewer).
In [1]: import pyopenjtalk
In [2]: from scipy.io import wavfile
In [3]: x, sr = pyopenjtalk.tts("おめでとうございます")
In [4]: wavfile.write("test.wav", sr, x.astype(np.int16))In [1]: import pyopenjtalk
In [2]: pyopenjtalk.extract_fullcontext("こんにちは")
Out[2]:
['xx^xx-sil+k=o/A:xx+xx+xx/B:xx-xx_xx/C:xx_xx+xx/D:xx+xx_xx/E:xx_xx!xx_xx-xx/F:xx_xx#xx_xx@xx_xx|xx_xx/G:5_5%0_xx_xx/H:xx_xx/I:xx-xx@xx+xx&xx-xx|xx+xx/J:1_5/K:1+1-5',
'xx^sil-k+o=N/A:-4+1+5/B:xx-xx_xx/C:09_xx+xx/D:xx+xx_xx/E:xx_xx!xx_xx-xx/F:5_5#0_xx@1_1|1_5/G:xx_xx%xx_xx_xx/H:xx_xx/I:1-5@1+1&1-1|1+5/J:xx_xx/K:1+1-5',
'sil^k-o+N=n/A:-4+1+5/B:xx-xx_xx/C:09_xx+xx/D:xx+xx_xx/E:xx_xx!xx_xx-xx/F:5_5#0_xx@1_1|1_5/G:xx_xx%xx_xx_xx/H:xx_xx/I:1-5@1+1&1-1|1+5/J:xx_xx/K:1+1-5',
'k^o-N+n=i/A:-3+2+4/B:xx-xx_xx/C:09_xx+xx/D:xx+xx_xx/E:xx_xx!xx_xx-xx/F:5_5#0_xx@1_1|1_5/G:xx_xx%xx_xx_xx/H:xx_xx/I:1-5@1+1&1-1|1+5/J:xx_xx/K:1+1-5',
'o^N-n+i=ch/A:-2+3+3/B:xx-xx_xx/C:09_xx+xx/D:xx+xx_xx/E:xx_xx!xx_xx-xx/F:5_5#0_xx@1_1|1_5/G:xx_xx%xx_xx_xx/H:xx_xx/I:1-5@1+1&1-1|1+5/J:xx_xx/K:1+1-5',
'N^n-i+ch=i/A:-2+3+3/B:xx-xx_xx/C:09_xx+xx/D:xx+xx_xx/E:xx_xx!xx_xx-xx/F:5_5#0_xx@1_1|1_5/G:xx_xx%xx_xx_xx/H:xx_xx/I:1-5@1+1&1-1|1+5/J:xx_xx/K:1+1-5',
'n^i-ch+i=w/A:-1+4+2/B:xx-xx_xx/C:09_xx+xx/D:xx+xx_xx/E:xx_xx!xx_xx-xx/F:5_5#0_xx@1_1|1_5/G:xx_xx%xx_xx_xx/H:xx_xx/I:1-5@1+1&1-1|1+5/J:xx_xx/K:1+1-5',
'i^ch-i+w=a/A:-1+4+2/B:xx-xx_xx/C:09_xx+xx/D:xx+xx_xx/E:xx_xx!xx_xx-xx/F:5_5#0_xx@1_1|1_5/G:xx_xx%xx_xx_xx/H:xx_xx/I:1-5@1+1&1-1|1+5/J:xx_xx/K:1+1-5',
'ch^i-w+a=sil/A:0+5+1/B:xx-xx_xx/C:09_xx+xx/D:xx+xx_xx/E:xx_xx!xx_xx-xx/F:5_5#0_xx@1_1|1_5/G:xx_xx%xx_xx_xx/H:xx_xx/I:1-5@1+1&1-1|1+5/J:xx_xx/K:1+1-5',
'i^w-a+sil=xx/A:0+5+1/B:xx-xx_xx/C:09_xx+xx/D:xx+xx_xx/E:xx_xx!xx_xx-xx/F:5_5#0_xx@1_1|1_5/G:xx_xx%xx_xx_xx/H:xx_xx/I:1-5@1+1&1-1|1+5/J:xx_xx/K:1+1-5',
'w^a-sil+xx=xx/A:xx+xx+xx/B:xx-xx_xx/C:xx_xx+xx/D:xx+xx_xx/E:5_5!0_xx-xx/F:xx_xx#xx_xx@xx_xx|xx_xx/G:xx_xx%xx_xx_xx/H:1_5/I:xx-xx@xx+xx&xx-xx|xx+xx/J:xx_xx/K:1+1-5']Please check lab_format.pdf in HTS-demo_NIT-ATR503-M001.tar.bz2 for more details about full-context labels.
In [1]: import pyopenjtalk
In [2]: pyopenjtalk.g2p("こんにちは")
Out[2]: 'k o N n i ch i w a'
In [3]: pyopenjtalk.g2p("こんにちは", kana=True)
Out[3]: 'コンニチワ'- Create a CSV file (e.g.
user.csv) and write custom words like below:
ＧＮＵ,,,1,名詞,一般,*,*,*,*,ＧＮＵ,グヌー,グヌー,2/3,*
- Call
mecab_dict_indexto compile the CSV file.
In [1]: import pyopenjtalk
In [2]: pyopenjtalk.mecab_dict_index("user.csv", "user.dic")
reading user.csv ... 1
emitting double-array: 100% |###########################################|
done!- Call
update_global_jtalk_with_user_dictto apply the user dictionary.
In [3]: pyopenjtalk.g2p("GNU")
Out[3]: 'j i i e n u y u u'
In [4]: pyopenjtalk.update_global_jtalk_with_user_dict("user.dic")
In [5]: pyopenjtalk.g2p("GNU")
Out[5]: 'g u n u u'After v0.3.0, the run_marine option has been available for estimating the Japanese accent with the DNN-based method (see marine). If you want to use the feature, please install pyopenjtalk as below;
pip install pyopenjtalk[marine]And then, you can use the option as the following examples;
In [1]: import pyopenjtalk
In [2]: x, sr = pyopenjtalk.tts("おめでとうございます", run_marine=True) # for TTS
In [3]: label = pyopenjtalk.extract_fullcontext("こんにちは", run_marine=True) # for text processing frontend only- pyopenjtalk: MIT license (LICENSE.md)
- Open JTalk: Modified BSD license (COPYING)
- htsvoice in this repository: Please check pyopenjtalk/htsvoice/README.md.
- marine: Apache 2.0 license (LICENSE)
HTS Working Group for their dedicated efforts to develop and maintain Open JTalk.
