From cba938fe22511099647a125c03aae8e9c64afbd7 Mon Sep 17 00:00:00 2001 From: Claudio Santini Date: Mon, 3 Feb 2025 12:29:19 +0100 Subject: [PATCH] japanese and chinese --- poetry.lock | 254 +++++++++++++++++++++++++++++++++------------- pyproject.toml | 5 +- test/test_main.py | 4 + 3 files changed, 193 insertions(+), 70 deletions(-) diff --git a/poetry.lock b/poetry.lock index 91bee9d..09141a0 100644 --- a/poetry.lock +++ b/poetry.lock @@ -22,18 +22,18 @@ tests-mypy = ["mypy (>=1.11.1)", "pytest-mypy-plugins"] [[package]] name = "babel" -version = "2.16.0" +version = "2.17.0" description = "Internationalization utilities" optional = false python-versions = ">=3.8" groups = ["main"] files = [ - {file = "babel-2.16.0-py3-none-any.whl", hash = "sha256:368b5b98b37c06b7daf6696391c3240c938b37767d4584413e8438c5c435fa8b"}, - {file = "babel-2.16.0.tar.gz", hash = "sha256:d1f3554ca26605fe173f3de0c65f750f5a42f924499bf134de6423582298e316"}, + {file = "babel-2.17.0-py3-none-any.whl", hash = "sha256:4d0b53093fdfb4b21c92b5213dba5a1b23885afa8383709427046b21c366e5f2"}, + {file = "babel-2.17.0.tar.gz", hash = "sha256:0c54cffb19f690cdcc52a3b50bcbf71e07a808d1c80d549f2459b9d2cf0afb9d"}, ] [package.extras] -dev = ["freezegun (>=1.0,<2.0)", "pytest (>=6.0)", "pytest-cov"] +dev = ["backports.zoneinfo", "freezegun (>=1.0,<2.0)", "jinja2 (>=3.0)", "pytest (>=6.0)", "pytest-cov", "pytz", "setuptools", "tzdata"] [[package]] name = "beautifulsoup4" @@ -403,6 +403,21 @@ azure = ["azure-storage-blob (>=12)", "azure-storage-file-datalake (>=12)"] gs = ["google-cloud-storage"] s3 = ["boto3 (>=1.34.0)"] +[[package]] +name = "cn2an" +version = "0.5.23" +description = "Convert Chinese numerals and Arabic numerals." +optional = false +python-versions = ">=3.6" +groups = ["main"] +files = [ + {file = "cn2an-0.5.23-py3-none-any.whl", hash = "sha256:b19ab3c53676765c038ccdab51f69b7efa4f0b888139c34088935769241f1cbf"}, + {file = "cn2an-0.5.23.tar.gz", hash = "sha256:eda06a63e5eff4a64488d9f22e5f2a4ceca6eaa63416e4f771e67edecb1a5bdb"}, +] + +[package.dependencies] +proces = ">=0.1.7" + [[package]] name = "colorama" version = "0.4.6" @@ -678,14 +693,14 @@ typing = ["typing-extensions (>=4.12.2)"] [[package]] name = "fsspec" -version = "2024.12.0" +version = "2025.2.0" description = "File-system specification" optional = false python-versions = ">=3.8" groups = ["main"] files = [ - {file = "fsspec-2024.12.0-py3-none-any.whl", hash = "sha256:b520aed47ad9804237ff878b504267a3b0b441e97508bd6d2d8774e3db85cee2"}, - {file = "fsspec-2024.12.0.tar.gz", hash = "sha256:670700c977ed2fb51e0d9f9253177ed20cbde4a3e5c0283cc5385b5870c8533f"}, + {file = "fsspec-2025.2.0-py3-none-any.whl", hash = "sha256:9de2ad9ce1f85e1931858535bc882543171d197001a0a5eb2ddc04f1781ab95b"}, + {file = "fsspec-2025.2.0.tar.gz", hash = "sha256:1c24b16eaa0a1798afa0337aa0db9b256718ab2a89c425371f5628d22c3b6afd"}, ] [package.extras] @@ -712,20 +727,20 @@ sftp = ["paramiko"] smb = ["smbprotocol"] ssh = ["paramiko"] test = ["aiohttp (!=4.0.0a0,!=4.0.0a1)", "numpy", "pytest", "pytest-asyncio (!=0.22.0)", "pytest-benchmark", "pytest-cov", "pytest-mock", "pytest-recording", "pytest-rerunfailures", "requests"] -test-downstream = ["aiobotocore (>=2.5.4,<3.0.0)", "dask-expr", "dask[dataframe,test]", "moto[server] (>4,<5)", "pytest-timeout", "xarray"] +test-downstream = ["aiobotocore (>=2.5.4,<3.0.0)", "dask[dataframe,test]", "moto[server] (>4,<5)", "pytest-timeout", "xarray"] test-full = ["adlfs", "aiohttp (!=4.0.0a0,!=4.0.0a1)", "cloudpickle", "dask", "distributed", "dropbox", "dropboxdrivefs", "fastparquet", "fusepy", "gcsfs", "jinja2", "kerchunk", "libarchive-c", "lz4", "notebook", "numpy", "ocifs", "pandas", "panel", "paramiko", "pyarrow", "pyarrow (>=1)", "pyftpdlib", "pygit2", "pytest", "pytest-asyncio (!=0.22.0)", "pytest-benchmark", "pytest-cov", "pytest-mock", "pytest-recording", "pytest-rerunfailures", "python-snappy", "requests", "smbprotocol", "tqdm", "urllib3", "zarr", "zstandard"] tqdm = ["tqdm"] [[package]] name = "huggingface-hub" -version = "0.28.0" +version = "0.28.1" description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub" optional = false python-versions = ">=3.8.0" groups = ["main"] files = [ - {file = "huggingface_hub-0.28.0-py3-none-any.whl", hash = "sha256:71cff4e500efe68061d94b7f6d3114e183715088be7a90bf4dd84af83b5f5cdb"}, - {file = "huggingface_hub-0.28.0.tar.gz", hash = "sha256:c2b18c02a47d4384763caddb4d0ab2a8fc6c16e0800d6de4d55d0a896244aba3"}, + {file = "huggingface_hub-0.28.1-py3-none-any.whl", hash = "sha256:aa6b9a3ffdae939b72c464dbb0d7f99f56e649b55c3d52406f49e0a5a620c0a7"}, + {file = "huggingface_hub-0.28.1.tar.gz", hash = "sha256:893471090c98e3b6efbdfdacafe4052b20b84d59866fb6f54c33d9af18c303ae"}, ] [package.dependencies] @@ -803,6 +818,17 @@ files = [ {file = "isodate-0.7.2.tar.gz", hash = "sha256:4cd1aa0f43ca76f4a6c6c0292a85f40b35ec2e43e315b59f06e6d32171a953e6"}, ] +[[package]] +name = "jieba" +version = "0.42.1" +description = "Chinese Words Segmentation Utilities" +optional = false +python-versions = "*" +groups = ["main"] +files = [ + {file = "jieba-0.42.1.tar.gz", hash = "sha256:055ca12f62674fafed09427f176506079bc135638a14e23e25be909131928db2"}, +] + [[package]] name = "jinja2" version = "3.1.5" @@ -872,19 +898,20 @@ referencing = ">=0.31.0" [[package]] name = "kokoro" -version = "0.2.3" +version = "0.3.5" description = "TTS" optional = false -python-versions = ">=3.6" +python-versions = ">=3.7" groups = ["main"] files = [ - {file = "kokoro-0.2.3-py3-none-any.whl", hash = "sha256:20eee4bb4bc37af6b5f093db2e058f8e7a6519c2448976ebd5ced6319e224109"}, - {file = "kokoro-0.2.3.tar.gz", hash = "sha256:b91440f3cb990697bbcd834ec6cae627a6c75a2cf7ec7b7d3533c29d70971d66"}, + {file = "kokoro-0.3.5-py3-none-any.whl", hash = "sha256:995c2284c13b49657df4280cda171ce03442b223ac97d3ca63f9a914b246a4ca"}, + {file = "kokoro-0.3.5.tar.gz", hash = "sha256:9eb456a8c005f7bfae4756b9718f0a39dd8a1216092e52d17a568e106c02f278"}, ] [package.dependencies] huggingface-hub = "*" -misaki = {version = ">=0.6.1", extras = ["en"]} +loguru = "*" +misaki = {version = ">=0.6.7", extras = ["en"]} numpy = "1.26.4" scipy = "*" torch = "*" @@ -940,6 +967,25 @@ files = [ {file = "language_tags-1.2.0.tar.gz", hash = "sha256:e934acba3e3dc85f867703eca421847a9ab7b7679b11b5d5cfd096febbf8bde6"}, ] +[[package]] +name = "loguru" +version = "0.7.3" +description = "Python logging made (stupidly) simple" +optional = false +python-versions = "<4.0,>=3.5" +groups = ["main"] +files = [ + {file = "loguru-0.7.3-py3-none-any.whl", hash = "sha256:31a33c10c8e1e10422bfd431aeb5d351c7cf7fa671e3c4df004162264b28220c"}, + {file = "loguru-0.7.3.tar.gz", hash = "sha256:19480589e77d47b8d85b2c827ad95d49bf31b0dcde16593892eb51dd18706eb6"}, +] + +[package.dependencies] +colorama = {version = ">=0.3.4", markers = "sys_platform == \"win32\""} +win32-setctime = {version = ">=1.0.0", markers = "sys_platform == \"win32\""} + +[package.extras] +dev = ["Sphinx (==8.1.3)", "build (==1.2.2)", "colorama (==0.4.5)", "colorama (==0.4.6)", "exceptiongroup (==1.1.3)", "freezegun (==1.1.0)", "freezegun (==1.5.0)", "mypy (==v0.910)", "mypy (==v0.971)", "mypy (==v1.13.0)", "mypy (==v1.4.1)", "myst-parser (==4.0.0)", "pre-commit (==4.0.1)", "pytest (==6.1.2)", "pytest (==8.3.2)", "pytest-cov (==2.12.1)", "pytest-cov (==5.0.0)", "pytest-cov (==6.0.0)", "pytest-mypy-plugins (==1.9.3)", "pytest-mypy-plugins (==3.1.0)", "sphinx-rtd-theme (==3.0.2)", "tox (==3.27.1)", "tox (==4.23.2)", "twine (==6.0.1)"] + [[package]] name = "lxml" version = "5.3.0" @@ -1279,19 +1325,23 @@ files = [ [[package]] name = "misaki" -version = "0.6.3" +version = "0.6.7" description = "G2P engine for TTS" optional = false python-versions = ">=3.7" groups = ["main"] files = [ - {file = "misaki-0.6.3-py3-none-any.whl", hash = "sha256:0b8fb39f1c7184a97ec82663f6ecfcc118c2e73b91b9c9d8cd26252510dd6d25"}, - {file = "misaki-0.6.3.tar.gz", hash = "sha256:f33903e959d4dbe5aee9e69748600cf31c0f0e98125d63a27ac8288d6860d641"}, + {file = "misaki-0.6.7-py3-none-any.whl", hash = "sha256:66a74d5ece8e882315ddf97f5ac4260b77ad52a8d038a54b1f0b366943eee782"}, + {file = "misaki-0.6.7.tar.gz", hash = "sha256:47233eb86623f615301dba24863bece9a21d969fc7ec46e035ce09995e8bde67"}, ] [package.dependencies] +cn2an = {version = "*", optional = true, markers = "extra == \"zh\""} +jieba = {version = "*", optional = true, markers = "extra == \"zh\""} num2words = {version = "*", optional = true, markers = "extra == \"en\""} +ordered-set = {version = "*", optional = true, markers = "extra == \"zh\""} phonemizer = {version = "*", optional = true, markers = "extra == \"en\""} +pypinyin = {version = "*", optional = true, markers = "extra == \"zh\""} regex = "*" spacy = {version = "*", optional = true, markers = "extra == \"en\""} spacy-curated-transformers = {version = "*", optional = true, markers = "extra == \"en\""} @@ -1301,7 +1351,7 @@ en = ["num2words", "phonemizer", "spacy", "spacy-curated-transformers"] ja = ["fugashi", "jaconv", "mojimoji", "unidic-lite"] ko = ["g2pk2"] vi = ["num2words", "spacy", "spacy-curated-transformers", "underthesea"] -zh = ["jieba", "ordered-set", "pypinyin"] +zh = ["cn2an", "jieba", "ordered-set", "pypinyin"] [[package]] name = "mpmath" @@ -1586,6 +1636,20 @@ files = [ [package.dependencies] nvidia-nvjitlink-cu12 = "*" +[[package]] +name = "nvidia-cusparselt-cu12" +version = "0.6.2" +description = "NVIDIA cuSPARSELt" +optional = false +python-versions = "*" +groups = ["main"] +markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\"" +files = [ + {file = "nvidia_cusparselt_cu12-0.6.2-py3-none-manylinux2014_aarch64.whl", hash = "sha256:067a7f6d03ea0d4841c85f0c6f1991c5dda98211f6302cb83a4ab234ee95bef8"}, + {file = "nvidia_cusparselt_cu12-0.6.2-py3-none-manylinux2014_x86_64.whl", hash = "sha256:df2c24502fd76ebafe7457dbc4716b2fec071aabaed4fb7691a201cde03704d9"}, + {file = "nvidia_cusparselt_cu12-0.6.2-py3-none-win_amd64.whl", hash = "sha256:0057c91d230703924c0422feabe4ce768841f9b4b44d28586b6f6d2eb86fbe70"}, +] + [[package]] name = "nvidia-nccl-cu12" version = "2.21.5" @@ -1626,6 +1690,21 @@ files = [ {file = "nvidia_nvtx_cu12-12.4.127-py3-none-win_amd64.whl", hash = "sha256:641dccaaa1139f3ffb0d3164b4b84f9d253397e38246a4f2f36728b48566d485"}, ] +[[package]] +name = "ordered-set" +version = "4.1.0" +description = "An OrderedSet is a custom MutableSet that remembers its order, so that every" +optional = false +python-versions = ">=3.7" +groups = ["main"] +files = [ + {file = "ordered-set-4.1.0.tar.gz", hash = "sha256:694a8e44c87657c59292ede72891eb91d34131f6531463aab3009191c77364a8"}, + {file = "ordered_set-4.1.0-py3-none-any.whl", hash = "sha256:046e1132c71fcf3330438a539928932caf51ddbc582496833e23de611de14562"}, +] + +[package.extras] +dev = ["black", "mypy", "pytest"] + [[package]] name = "packaging" version = "24.2" @@ -1723,6 +1802,18 @@ files = [ cymem = ">=2.0.2,<2.1.0" murmurhash = ">=0.28.0,<1.1.0" +[[package]] +name = "proces" +version = "0.1.7" +description = "text preprocess." +optional = false +python-versions = ">=3.6" +groups = ["main"] +files = [ + {file = "proces-0.1.7-py3-none-any.whl", hash = "sha256:308325bbc96877263f06e57e5e9c760c4b42cc722887ad60be6b18fc37d68762"}, + {file = "proces-0.1.7.tar.gz", hash = "sha256:70a05d9e973dd685f7a9092c58be695a8181a411d63796c213232fd3fdc43775"}, +] + [[package]] name = "pycparser" version = "2.22" @@ -1840,6 +1931,18 @@ files = [ [package.extras] diagrams = ["jinja2", "railroad-diagrams"] +[[package]] +name = "pypinyin" +version = "0.53.0" +description = "汉字拼音转换模块/工具." +optional = false +python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,<4,>=2.6" +groups = ["main"] +files = [ + {file = "pypinyin-0.53.0-py2.py3-none-any.whl", hash = "sha256:a906768919da3c31771f2c5e0e5a759214dc38d0087e15e6ff67649e03df8097"}, + {file = "pypinyin-0.53.0.tar.gz", hash = "sha256:a2d39ddc2bd31b55897bbb10d2e11a0c4d399988a97c00ad489c151afd9b106d"}, +] + [[package]] name = "python-dateutil" version = "2.9.0.post0" @@ -1920,28 +2023,26 @@ files = [ [[package]] name = "rdflib" -version = "6.2.0" +version = "7.1.3" description = "RDFLib is a Python library for working with RDF, a simple yet powerful language for representing information." optional = false -python-versions = ">=3.7" +python-versions = "<4.0.0,>=3.8.1" groups = ["main"] files = [ - {file = "rdflib-6.2.0-py3-none-any.whl", hash = "sha256:85c34a86dfc517a41e5f2425a41a0aceacc23983462b32e68610b9fad1383bca"}, - {file = "rdflib-6.2.0.tar.gz", hash = "sha256:62dc3c86d1712db0f55785baf8047f63731fa59b2682be03219cb89262065942"}, + {file = "rdflib-7.1.3-py3-none-any.whl", hash = "sha256:5402310a9f0f3c07d453d73fd0ad6ba35616286fe95d3670db2b725f3f539673"}, + {file = "rdflib-7.1.3.tar.gz", hash = "sha256:f3dcb4c106a8cd9e060d92f43d593d09ebc3d07adc244f4c7315856a12e383ee"}, ] [package.dependencies] -isodate = "*" -pyparsing = "*" -setuptools = "*" +isodate = {version = ">=0.7.2,<1.0.0", markers = "python_version < \"3.11\""} +pyparsing = ">=2.1.0,<4" [package.extras] -berkeleydb = ["berkeleydb"] -dev = ["black (==22.6.0)", "flake8", "flakeheaven", "isort", "mypy", "pep8-naming", "types-setuptools"] -docs = ["myst-parser", "sphinx (<6)", "sphinx-autodoc-typehints", "sphinxcontrib-apidoc", "sphinxcontrib-kroki"] -html = ["html5lib"] -networkx = ["networkx"] -tests = ["html5lib", "pytest", "pytest-cov"] +berkeleydb = ["berkeleydb (>=18.1.0,<19.0.0)"] +html = ["html5rdf (>=1.2,<2)"] +lxml = ["lxml (>=4.3,<6.0)"] +networkx = ["networkx (>=2,<4)"] +orjson = ["orjson (>=3.9.14,<4)"] [[package]] name = "referencing" @@ -2783,29 +2884,32 @@ files = [ [[package]] name = "torch" -version = "2.5.1" +version = "2.6.0" description = "Tensors and Dynamic neural networks in Python with strong GPU acceleration" optional = false -python-versions = ">=3.8.0" +python-versions = ">=3.9.0" groups = ["main"] files = [ - {file = "torch-2.5.1-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:71328e1bbe39d213b8721678f9dcac30dfc452a46d586f1d514a6aa0a99d4744"}, - {file = "torch-2.5.1-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:34bfa1a852e5714cbfa17f27c49d8ce35e1b7af5608c4bc6e81392c352dbc601"}, - {file = "torch-2.5.1-cp310-cp310-win_amd64.whl", hash = "sha256:32a037bd98a241df6c93e4c789b683335da76a2ac142c0973675b715102dc5fa"}, - {file = "torch-2.5.1-cp310-none-macosx_11_0_arm64.whl", hash = "sha256:23d062bf70776a3d04dbe74db950db2a5245e1ba4f27208a87f0d743b0d06e86"}, - {file = "torch-2.5.1-cp311-cp311-manylinux1_x86_64.whl", hash = "sha256:de5b7d6740c4b636ef4db92be922f0edc425b65ed78c5076c43c42d362a45457"}, - {file = "torch-2.5.1-cp311-cp311-manylinux2014_aarch64.whl", hash = "sha256:340ce0432cad0d37f5a31be666896e16788f1adf8ad7be481196b503dad675b9"}, - {file = "torch-2.5.1-cp311-cp311-win_amd64.whl", hash = "sha256:603c52d2fe06433c18b747d25f5c333f9c1d58615620578c326d66f258686f9a"}, - {file = "torch-2.5.1-cp311-none-macosx_11_0_arm64.whl", hash = "sha256:31f8c39660962f9ae4eeec995e3049b5492eb7360dd4f07377658ef4d728fa4c"}, - {file = "torch-2.5.1-cp312-cp312-manylinux1_x86_64.whl", hash = "sha256:ed231a4b3a5952177fafb661213d690a72caaad97d5824dd4fc17ab9e15cec03"}, - {file = "torch-2.5.1-cp312-cp312-manylinux2014_aarch64.whl", hash = "sha256:3f4b7f10a247e0dcd7ea97dc2d3bfbfc90302ed36d7f3952b0008d0df264e697"}, - {file = "torch-2.5.1-cp312-cp312-win_amd64.whl", hash = "sha256:73e58e78f7d220917c5dbfad1a40e09df9929d3b95d25e57d9f8558f84c9a11c"}, - {file = "torch-2.5.1-cp312-none-macosx_11_0_arm64.whl", hash = "sha256:8c712df61101964eb11910a846514011f0b6f5920c55dbf567bff8a34163d5b1"}, - {file = "torch-2.5.1-cp313-cp313-manylinux1_x86_64.whl", hash = "sha256:9b61edf3b4f6e3b0e0adda8b3960266b9009d02b37555971f4d1c8f7a05afed7"}, - {file = "torch-2.5.1-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:1f3b7fb3cf7ab97fae52161423f81be8c6b8afac8d9760823fd623994581e1a3"}, - {file = "torch-2.5.1-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:7974e3dce28b5a21fb554b73e1bc9072c25dde873fa00d54280861e7a009d7dc"}, - {file = "torch-2.5.1-cp39-cp39-win_amd64.whl", hash = "sha256:46c817d3ea33696ad3b9df5e774dba2257e9a4cd3c4a3afbf92f6bb13ac5ce2d"}, - {file = "torch-2.5.1-cp39-none-macosx_11_0_arm64.whl", hash = "sha256:8046768b7f6d35b85d101b4b38cba8aa2f3cd51952bc4c06a49580f2ce682291"}, + {file = "torch-2.6.0-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:6860df13d9911ac158f4c44031609700e1eba07916fff62e21e6ffa0a9e01961"}, + {file = "torch-2.6.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:c4f103a49830ce4c7561ef4434cc7926e5a5fe4e5eb100c19ab36ea1e2b634ab"}, + {file = "torch-2.6.0-cp310-cp310-win_amd64.whl", hash = "sha256:56eeaf2ecac90da5d9e35f7f35eb286da82673ec3c582e310a8d1631a1c02341"}, + {file = "torch-2.6.0-cp310-none-macosx_11_0_arm64.whl", hash = "sha256:09e06f9949e1a0518c5b09fe95295bc9661f219d9ecb6f9893e5123e10696628"}, + {file = "torch-2.6.0-cp311-cp311-manylinux1_x86_64.whl", hash = "sha256:7979834102cd5b7a43cc64e87f2f3b14bd0e1458f06e9f88ffa386d07c7446e1"}, + {file = "torch-2.6.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:ccbd0320411fe1a3b3fec7b4d3185aa7d0c52adac94480ab024b5c8f74a0bf1d"}, + {file = "torch-2.6.0-cp311-cp311-win_amd64.whl", hash = "sha256:46763dcb051180ce1ed23d1891d9b1598e07d051ce4c9d14307029809c4d64f7"}, + {file = "torch-2.6.0-cp311-none-macosx_11_0_arm64.whl", hash = "sha256:94fc63b3b4bedd327af588696559f68c264440e2503cc9e6954019473d74ae21"}, + {file = "torch-2.6.0-cp312-cp312-manylinux1_x86_64.whl", hash = "sha256:2bb8987f3bb1ef2675897034402373ddfc8f5ef0e156e2d8cfc47cacafdda4a9"}, + {file = "torch-2.6.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:b789069020c5588c70d5c2158ac0aa23fd24a028f34a8b4fcb8fcb4d7efcf5fb"}, + {file = "torch-2.6.0-cp312-cp312-win_amd64.whl", hash = "sha256:7e1448426d0ba3620408218b50aa6ada88aeae34f7a239ba5431f6c8774b1239"}, + {file = "torch-2.6.0-cp312-none-macosx_11_0_arm64.whl", hash = "sha256:9a610afe216a85a8b9bc9f8365ed561535c93e804c2a317ef7fabcc5deda0989"}, + {file = "torch-2.6.0-cp313-cp313-manylinux1_x86_64.whl", hash = "sha256:4874a73507a300a5d089ceaff616a569e7bb7c613c56f37f63ec3ffac65259cf"}, + {file = "torch-2.6.0-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:a0d5e1b9874c1a6c25556840ab8920569a7a4137afa8a63a32cee0bc7d89bd4b"}, + {file = "torch-2.6.0-cp313-cp313-win_amd64.whl", hash = "sha256:510c73251bee9ba02ae1cb6c9d4ee0907b3ce6020e62784e2d7598e0cfa4d6cc"}, + {file = "torch-2.6.0-cp313-none-macosx_11_0_arm64.whl", hash = "sha256:ff96f4038f8af9f7ec4231710ed4549da1bdebad95923953a25045dcf6fd87e2"}, + {file = "torch-2.6.0-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:9ea955317cfcd3852b1402b62af258ce735c2edeee42ca9419b6bc889e5ae053"}, + {file = "torch-2.6.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:bb2c6c3e65049f081940f5ab15c9136c7de40d3f01192541c920a07c7c585b7e"}, + {file = "torch-2.6.0-cp39-cp39-win_amd64.whl", hash = "sha256:683410f97984103148e31b38a8631acf31c3034c020c0f4d26171e7626d8317a"}, + {file = "torch-2.6.0-cp39-none-macosx_11_0_arm64.whl", hash = "sha256:265f70de5fd45b864d924b64be1797f86e76c8e48a02c2a3a6fc7ec247d2226c"}, ] [package.dependencies] @@ -2822,17 +2926,18 @@ nvidia-cufft-cu12 = {version = "11.2.1.3", markers = "platform_system == \"Linux nvidia-curand-cu12 = {version = "10.3.5.147", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} nvidia-cusolver-cu12 = {version = "11.6.1.9", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} nvidia-cusparse-cu12 = {version = "12.3.1.170", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +nvidia-cusparselt-cu12 = {version = "0.6.2", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} nvidia-nccl-cu12 = {version = "2.21.5", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} nvidia-nvjitlink-cu12 = {version = "12.4.127", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} nvidia-nvtx-cu12 = {version = "12.4.127", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} setuptools = {version = "*", markers = "python_version >= \"3.12\""} sympy = {version = "1.13.1", markers = "python_version >= \"3.9\""} -triton = {version = "3.1.0", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version < \"3.13\""} -typing-extensions = ">=4.8.0" +triton = {version = "3.2.0", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +typing-extensions = ">=4.10.0" [package.extras] opt-einsum = ["opt-einsum (>=3.3)"] -optree = ["optree (>=0.12.0)"] +optree = ["optree (>=0.13.0)"] [[package]] name = "tqdm" @@ -2858,14 +2963,14 @@ telegram = ["requests"] [[package]] name = "transformers" -version = "4.48.1" +version = "4.48.2" description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow" optional = false python-versions = ">=3.9.0" groups = ["main"] files = [ - {file = "transformers-4.48.1-py3-none-any.whl", hash = "sha256:24be0564b0a36d9e433d9a65de248f1545b6f6edce1737669605eb6a8141bbbb"}, - {file = "transformers-4.48.1.tar.gz", hash = "sha256:7c1931facc3ee8adcbf86fc7a87461d54c1e40eca3bb57fef1ee9f3ecd32187e"}, + {file = "transformers-4.48.2-py3-none-any.whl", hash = "sha256:493bc5b0268b116eff305edf6656367fc89cf570e7a9d5891369e04751db698a"}, + {file = "transformers-4.48.2.tar.gz", hash = "sha256:dcfb73473e61f22fb3366fe2471ed2e42779ecdd49527a1bdf1937574855d516"}, ] [package.dependencies] @@ -2928,23 +3033,20 @@ vision = ["Pillow (>=10.0.1,<=15.0)"] [[package]] name = "triton" -version = "3.1.0" +version = "3.2.0" description = "A language and compiler for custom Deep Learning operations" optional = false python-versions = "*" groups = ["main"] markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\"" files = [ - {file = "triton-3.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6b0dd10a925263abbe9fa37dcde67a5e9b2383fc269fdf59f5657cac38c5d1d8"}, - {file = "triton-3.1.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0f34f6e7885d1bf0eaaf7ba875a5f0ce6f3c13ba98f9503651c1e6dc6757ed5c"}, - {file = "triton-3.1.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c8182f42fd8080a7d39d666814fa36c5e30cc00ea7eeeb1a2983dbb4c99a0fdc"}, - {file = "triton-3.1.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6dadaca7fc24de34e180271b5cf864c16755702e9f63a16f62df714a8099126a"}, - {file = "triton-3.1.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:aafa9a20cd0d9fee523cd4504aa7131807a864cd77dcf6efe7e981f18b8c6c11"}, + {file = "triton-3.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b3e54983cd51875855da7c68ec05c05cf8bb08df361b1d5b69e05e40b0c9bd62"}, + {file = "triton-3.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8009a1fb093ee8546495e96731336a33fb8856a38e45bb4ab6affd6dbc3ba220"}, + {file = "triton-3.2.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8d9b215efc1c26fa7eefb9a157915c92d52e000d2bf83e5f69704047e63f125c"}, + {file = "triton-3.2.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e5dfa23ba84541d7c0a531dfce76d8bcd19159d50a4a8b14ad01e91734a5c1b0"}, + {file = "triton-3.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:30ceed0eff2c4a73b14eb63e052992f44bbdf175f3fad21e1ac8097a772de7ee"}, ] -[package.dependencies] -filelock = "*" - [package.extras] build = ["cmake (>=3.20)", "lit"] tests = ["autopep8", "flake8", "isort", "llnl-hatchet", "numpy", "pytest", "scipy (>=1.7.1)"] @@ -3060,6 +3162,22 @@ srsly = ">=2.4.3,<3.0.0" typer = ">=0.3.0,<1.0.0" wasabi = ">=0.9.1,<1.2.0" +[[package]] +name = "win32-setctime" +version = "1.2.0" +description = "A small Python utility to set file creation time on Windows" +optional = false +python-versions = ">=3.5" +groups = ["main"] +markers = "sys_platform == \"win32\"" +files = [ + {file = "win32_setctime-1.2.0-py3-none-any.whl", hash = "sha256:95d644c4e708aba81dc3704a116d8cbc974d70b3bdb8be1d150e36be6e9d1390"}, + {file = "win32_setctime-1.2.0.tar.gz", hash = "sha256:ae1fdf948f5640aae05c511ade119313fb6a30d7eabe25fef9764dca5873c4c0"}, +] + +[package.extras] +dev = ["black (>=19.3b0)", "pytest (>=4.6.2)"] + [[package]] name = "windows-curses" version = "2.4.1" @@ -3215,4 +3333,4 @@ type = ["pytest-mypy"] [metadata] lock-version = "2.1" python-versions = ">=3.9,<3.13" -content-hash = "4e62920e0cb502d8f9a30a463d8266939ac0d3e6bcfe5d4f26830b058b659561" +content-hash = "4457fbca8c8a609edea72cf65137b4a5c5ea501bd50744cb35706cdc277b3746" diff --git a/pyproject.toml b/pyproject.toml index fa9571c..6f07ef6 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -8,14 +8,15 @@ authors = [ readme = "README.md" requires-python = ">=3.9,<3.13" dependencies = [ - "kokoro (>=0.2.3,<0.3.0)", "ebooklib (>=0.18,<0.19)", "soundfile (>=0.13.1,<0.14.0)", "pick (>=2.4.0,<3.0.0)", "bs4 (>=0.0.2,<0.0.3)", "pydub (>=0.25.1,<0.26.0)", "spacy (>=3.8.3,<4.0.0)", - "yaspin (>=3.1.0,<4.0.0)" + "yaspin (>=3.1.0,<4.0.0)", + "kokoro (>=0.3.5,<0.4.0)", + "misaki[zh] (>=0.6.7,<0.7.0)" ] diff --git a/test/test_main.py b/test/test_main.py index 7c61cfb..6da640f 100644 --- a/test/test_main.py +++ b/test/test_main.py @@ -42,3 +42,7 @@ class MainTest(unittest.TestCase): def test_french_baudelaire(self): url = 'http://gallica.bnf.fr/ark:/12148/bpt6k70861t.epub' self.base('baudelaire', url, voice='ff_siwis') + + def test_chinese(self): + url = 'https://www.gutenberg.org/ebooks/24225.epub3.images' + self.base('chinese', url, voice='zf_xiaobei')