diff --git a/.github/assets/aau.png b/.github/assets/aau.png
new file mode 100644
index 0000000..d8f241c
Binary files /dev/null and b/.github/assets/aau.png differ
diff --git a/.github/assets/corti.png b/.github/assets/corti.png
new file mode 100644
index 0000000..24c29e6
Binary files /dev/null and b/.github/assets/corti.png differ
diff --git a/.github/assets/dtu.png b/.github/assets/dtu.png
new file mode 100644
index 0000000..d782f79
Binary files /dev/null and b/.github/assets/dtu.png differ
diff --git a/.github/assets/pcai.png b/.github/assets/pcai.png
new file mode 100644
index 0000000..d1ef1b8
Binary files /dev/null and b/.github/assets/pcai.png differ
diff --git a/.github/assets/ucph.png b/.github/assets/ucph.png
new file mode 100644
index 0000000..be08f64
Binary files /dev/null and b/.github/assets/ucph.png differ
diff --git a/README.md b/README.md
index fc0382c..5b04d12 100644
--- a/README.md
+++ b/README.md
@@ -98,6 +98,18 @@ __Notes:__
- Use the `--help` flag to see all available options for `transcribe_dataset.py` and `evaluate_dataset.py`.
- All results reported in the paper are based on the test sets.
+__Collaborators:__
+
+
+
+
+
---
diff --git a/poetry.lock b/poetry.lock
index b7bd26c..2deffd1 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -498,6 +498,23 @@ files = [
{file = "backoff-2.2.1.tar.gz", hash = "sha256:03f829f5bb1923180821643f8753b0502c3b682293992485b0eef2807afa5cba"},
]
+[[package]]
+name = "backports-tarfile"
+version = "1.2.0"
+description = "Backport of CPython tarfile module"
+optional = false
+python-versions = ">=3.8"
+groups = ["dev"]
+markers = "platform_machine != \"ppc64le\" and platform_machine != \"s390x\" and python_version == \"3.11\""
+files = [
+ {file = "backports.tarfile-1.2.0-py3-none-any.whl", hash = "sha256:77e284d754527b01fb1e6fa8a1afe577858ebe4e9dad8919e34c862cb399bc34"},
+ {file = "backports_tarfile-1.2.0.tar.gz", hash = "sha256:d75e02c268746e1b8144c278978b6e98e85de6ad16f8e4b0844a154557eca991"},
+]
+
+[package.extras]
+docs = ["furo", "jaraco.packaging (>=9.3)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
+testing = ["jaraco.test", "pytest (!=8.0.*)", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)"]
+
[[package]]
name = "bcrypt"
version = "5.0.0"
@@ -750,6 +767,27 @@ files = [
{file = "bracex-2.6.tar.gz", hash = "sha256:98f1347cd77e22ee8d967a30ad4e310b233f7754dbf31ff3fceb76145ba47dc7"},
]
+[[package]]
+name = "build"
+version = "1.3.0"
+description = "A simple, correct Python build frontend"
+optional = false
+python-versions = ">=3.9"
+groups = ["dev"]
+files = [
+ {file = "build-1.3.0-py3-none-any.whl", hash = "sha256:7145f0b5061ba90a1500d60bd1b13ca0a8a4cebdd0cc16ed8adf1c0e739f43b4"},
+ {file = "build-1.3.0.tar.gz", hash = "sha256:698edd0ea270bde950f53aed21f3a0135672206f3911e0176261a31e0e07b397"},
+]
+
+[package.dependencies]
+colorama = {version = "*", markers = "os_name == \"nt\""}
+packaging = ">=19.1"
+pyproject_hooks = "*"
+
+[package.extras]
+uv = ["uv (>=0.1.18)"]
+virtualenv = ["virtualenv (>=20.11) ; python_version < \"3.10\"", "virtualenv (>=20.17) ; python_version >= \"3.10\" and python_version < \"3.14\"", "virtualenv (>=20.31) ; python_version >= \"3.14\""]
+
[[package]]
name = "catalogue"
version = "2.0.10"
@@ -782,23 +820,22 @@ files = [
name = "certifi"
version = "2025.8.3"
description = "Python package for providing Mozilla's CA Bundle."
-optional = true
+optional = false
python-versions = ">=3.7"
-groups = ["main"]
-markers = "extra == \"evaluation\""
+groups = ["main", "dev"]
files = [
{file = "certifi-2025.8.3-py3-none-any.whl", hash = "sha256:f6c12493cfb1b06ba2ff328595af9350c65d6644968e5d3a2ffd78699af217a5"},
{file = "certifi-2025.8.3.tar.gz", hash = "sha256:e564105f78ded564e3ae7c923924435e1daa7463faeab5bb932bc53ffae63407"},
]
+markers = {main = "extra == \"evaluation\""}
[[package]]
name = "cffi"
version = "2.0.0"
description = "Foreign Function Interface for Python calling C code."
-optional = true
+optional = false
python-versions = ">=3.9"
-groups = ["main"]
-markers = "extra == \"evaluation\""
+groups = ["main", "dev"]
files = [
{file = "cffi-2.0.0-cp310-cp310-macosx_10_13_x86_64.whl", hash = "sha256:0cf2d91ecc3fcc0625c2c530fe004f82c110405f101548512cce44322fa8ac44"},
{file = "cffi-2.0.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:f73b96c41e3b2adedc34a7356e64c8eb96e03a3782b535e043a986276ce12a49"},
@@ -885,6 +922,7 @@ files = [
{file = "cffi-2.0.0-cp39-cp39-win_amd64.whl", hash = "sha256:b882b3df248017dba09d6b16defe9b5c407fe32fc7c65a9c69798e6175601be9"},
{file = "cffi-2.0.0.tar.gz", hash = "sha256:44d1b5909021139fe36001ae048dbdde8214afa20200eda0f64c068cac5d5529"},
]
+markers = {main = "extra == \"evaluation\"", dev = "platform_machine != \"ppc64le\" and platform_machine != \"s390x\" and sys_platform == \"linux\" and platform_python_implementation != \"PyPy\""}
[package.dependencies]
pycparser = {version = "*", markers = "implementation_name != \"PyPy\""}
@@ -918,10 +956,9 @@ files = [
name = "charset-normalizer"
version = "3.4.3"
description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
-optional = true
+optional = false
python-versions = ">=3.7"
-groups = ["main"]
-markers = "extra == \"evaluation\""
+groups = ["main", "dev"]
files = [
{file = "charset_normalizer-3.4.3-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:fb7f67a1bfa6e40b438170ebdc8158b78dc465a5a67b6dde178a46987b244a72"},
{file = "charset_normalizer-3.4.3-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:cc9370a2da1ac13f0153780040f465839e6cccb4a1e44810124b4e22483c93fe"},
@@ -1003,6 +1040,7 @@ files = [
{file = "charset_normalizer-3.4.3-py3-none-any.whl", hash = "sha256:ce571ab16d890d23b5c278547ba694193a45011ff86a9162a71307ed9f86759a"},
{file = "charset_normalizer-3.4.3.tar.gz", hash = "sha256:6fce4b8500244f6fcb71465d4a4930d132ba9ab8e71a7859e6a5d59851068d14"},
]
+markers = {main = "extra == \"evaluation\""}
[[package]]
name = "click"
@@ -1056,7 +1094,7 @@ files = [
{file = "colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6"},
{file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
]
-markers = {main = "platform_system == \"Windows\" or sys_platform == \"win32\" or extra == \"evaluation\"", dev = "sys_platform == \"win32\"", test = "sys_platform == \"win32\""}
+markers = {main = "platform_system == \"Windows\" or sys_platform == \"win32\" or extra == \"evaluation\"", dev = "sys_platform == \"win32\" or os_name == \"nt\"", test = "sys_platform == \"win32\""}
[[package]]
name = "colorlog"
@@ -1292,10 +1330,9 @@ toml = ["tomli ; python_full_version <= \"3.11.0a6\""]
name = "cryptography"
version = "42.0.8"
description = "cryptography is a package which provides cryptographic recipes and primitives to Python developers."
-optional = true
+optional = false
python-versions = ">=3.7"
-groups = ["main"]
-markers = "extra == \"evaluation\""
+groups = ["main", "dev"]
files = [
{file = "cryptography-42.0.8-cp37-abi3-macosx_10_12_universal2.whl", hash = "sha256:81d8a521705787afe7a18d5bfb47ea9d9cc068206270aad0b96a725022e18d2e"},
{file = "cryptography-42.0.8-cp37-abi3-macosx_10_12_x86_64.whl", hash = "sha256:961e61cefdcb06e0c6d7e3a1b22ebe8b996eb2bf50614e89384be54c48c6b63d"},
@@ -1330,6 +1367,7 @@ files = [
{file = "cryptography-42.0.8-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:013629ae70b40af70c9a7a5db40abe5d9054e6f4380e50ce769947b73bf3caad"},
{file = "cryptography-42.0.8.tar.gz", hash = "sha256:8d09d05439ce7baa8e9e95b07ec5b6c886f548deb7e0f69ef25f64b3bce842f2"},
]
+markers = {main = "extra == \"evaluation\"", dev = "platform_machine != \"ppc64le\" and platform_machine != \"s390x\" and sys_platform == \"linux\""}
[package.dependencies]
cffi = {version = ">=1.12", markers = "platform_python_implementation != \"PyPy\""}
@@ -1742,14 +1780,14 @@ test = ["pytest"]
name = "docutils"
version = "0.21.2"
description = "Docutils -- Python Documentation Utilities"
-optional = true
+optional = false
python-versions = ">=3.9"
-groups = ["main"]
-markers = "extra == \"evaluation\""
+groups = ["main", "dev"]
files = [
{file = "docutils-0.21.2-py3-none-any.whl", hash = "sha256:dafca5b9e384f0e419294eb4d2ff9fa826435bf15f15b7bd45723e8ad76811b2"},
{file = "docutils-0.21.2.tar.gz", hash = "sha256:3a6b18732edf182daa3cd12775bbb338cf5691468f91eeeb109deff6ebfa986f"},
]
+markers = {main = "extra == \"evaluation\""}
[[package]]
name = "editdistance"
@@ -2777,6 +2815,26 @@ antlr4-python3-runtime = "==4.9.*"
omegaconf = ">=2.2,<2.4"
packaging = "*"
+[[package]]
+name = "id"
+version = "1.5.0"
+description = "A tool for generating OIDC identities"
+optional = false
+python-versions = ">=3.8"
+groups = ["dev"]
+files = [
+ {file = "id-1.5.0-py3-none-any.whl", hash = "sha256:f1434e1cef91f2cbb8a4ec64663d5a23b9ed43ef44c4c957d02583d61714c658"},
+ {file = "id-1.5.0.tar.gz", hash = "sha256:292cb8a49eacbbdbce97244f47a97b4c62540169c976552e497fd57df0734c1d"},
+]
+
+[package.dependencies]
+requests = "*"
+
+[package.extras]
+dev = ["build", "bump (>=1.3.2)", "id[lint,test]"]
+lint = ["bandit", "interrogate", "mypy", "ruff (<0.8.2)", "types-requests"]
+test = ["coverage[toml]", "pretend", "pytest", "pytest-cov"]
+
[[package]]
name = "identify"
version = "2.6.14"
@@ -2796,14 +2854,14 @@ license = ["ukkonen"]
name = "idna"
version = "3.10"
description = "Internationalized Domain Names in Applications (IDNA)"
-optional = true
+optional = false
python-versions = ">=3.6"
-groups = ["main"]
-markers = "extra == \"evaluation\""
+groups = ["main", "dev"]
files = [
{file = "idna-3.10-py3-none-any.whl", hash = "sha256:946d195a0d259cbba61165e88e65941f16e9b36ea6ddb97f00452bae8b1287d3"},
{file = "idna-3.10.tar.gz", hash = "sha256:12f65c9b470abda6dc35cf8e63cc574b1c52b11df2c86030af0ac09b01b13ea9"},
]
+markers = {main = "extra == \"evaluation\""}
[package.extras]
all = ["flake8 (>=7.1.1)", "mypy (>=1.11.2)", "pytest (>=8.3.2)", "ruff (>=0.6.2)"]
@@ -2969,14 +3027,14 @@ files = [
name = "importlib-metadata"
version = "8.7.0"
description = "Read metadata from Python packages"
-optional = true
+optional = false
python-versions = ">=3.9"
-groups = ["main"]
-markers = "extra == \"evaluation\""
+groups = ["main", "dev"]
files = [
{file = "importlib_metadata-8.7.0-py3-none-any.whl", hash = "sha256:e5dd1551894c77868a30651cef00984d50e1002d06942a7101d34870c5f02afd"},
{file = "importlib_metadata-8.7.0.tar.gz", hash = "sha256:d13b81ad223b890aa16c5471f2ac3056cf76c5f10f82d6f9292f0b415f389000"},
]
+markers = {main = "extra == \"evaluation\"", dev = "platform_machine != \"ppc64le\" and platform_machine != \"s390x\" and python_version == \"3.11\""}
[package.dependencies]
zipp = ">=3.20"
@@ -3178,6 +3236,70 @@ files = [
{file = "Janome-0.5.0.tar.gz", hash = "sha256:ce4a3ed7a4635c2f80139639327d5b1e0381858ad74a3c4a61e8cc83f820400e"},
]
+[[package]]
+name = "jaraco-classes"
+version = "3.4.0"
+description = "Utility functions for Python class constructs"
+optional = false
+python-versions = ">=3.8"
+groups = ["dev"]
+markers = "platform_machine != \"ppc64le\" and platform_machine != \"s390x\""
+files = [
+ {file = "jaraco.classes-3.4.0-py3-none-any.whl", hash = "sha256:f662826b6bed8cace05e7ff873ce0f9283b5c924470fe664fff1c2f00f581790"},
+ {file = "jaraco.classes-3.4.0.tar.gz", hash = "sha256:47a024b51d0239c0dd8c8540c6c7f484be3b8fcf0b2d85c13825780d3b3f3acd"},
+]
+
+[package.dependencies]
+more-itertools = "*"
+
+[package.extras]
+docs = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
+testing = ["pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-mypy", "pytest-ruff (>=0.2.1)"]
+
+[[package]]
+name = "jaraco-context"
+version = "6.0.1"
+description = "Useful decorators and context managers"
+optional = false
+python-versions = ">=3.8"
+groups = ["dev"]
+markers = "platform_machine != \"ppc64le\" and platform_machine != \"s390x\""
+files = [
+ {file = "jaraco.context-6.0.1-py3-none-any.whl", hash = "sha256:f797fc481b490edb305122c9181830a3a5b76d84ef6d1aef2fb9b47ab956f9e4"},
+ {file = "jaraco_context-6.0.1.tar.gz", hash = "sha256:9bae4ea555cf0b14938dc0aee7c9f32ed303aa20a3b73e7dc80111628792d1b3"},
+]
+
+[package.dependencies]
+"backports.tarfile" = {version = "*", markers = "python_version < \"3.12\""}
+
+[package.extras]
+doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
+test = ["portend", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-mypy", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\""]
+
+[[package]]
+name = "jaraco-functools"
+version = "4.3.0"
+description = "Functools like those found in stdlib"
+optional = false
+python-versions = ">=3.9"
+groups = ["dev"]
+markers = "platform_machine != \"ppc64le\" and platform_machine != \"s390x\""
+files = [
+ {file = "jaraco_functools-4.3.0-py3-none-any.whl", hash = "sha256:227ff8ed6f7b8f62c56deff101545fa7543cf2c8e7b82a7c2116e672f29c26e8"},
+ {file = "jaraco_functools-4.3.0.tar.gz", hash = "sha256:cfd13ad0dd2c47a3600b439ef72d8615d482cedcff1632930d6f28924d92f294"},
+]
+
+[package.dependencies]
+more_itertools = "*"
+
+[package.extras]
+check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\""]
+cover = ["pytest-cov"]
+doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
+enabler = ["pytest-enabler (>=2.2)"]
+test = ["jaraco.classes", "pytest (>=6,!=8.1.*)"]
+type = ["pytest-mypy"]
+
[[package]]
name = "jedi"
version = "0.19.2"
@@ -3198,6 +3320,23 @@ docs = ["Jinja2 (==2.11.3)", "MarkupSafe (==1.1.1)", "Pygments (==2.8.1)", "alab
qa = ["flake8 (==5.0.4)", "mypy (==0.971)", "types-setuptools (==67.2.0.1)"]
testing = ["Django", "attrs", "colorama", "docopt", "pytest (<9.0.0)"]
+[[package]]
+name = "jeepney"
+version = "0.9.0"
+description = "Low-level, pure Python DBus protocol wrapper."
+optional = false
+python-versions = ">=3.7"
+groups = ["dev"]
+markers = "platform_machine != \"ppc64le\" and platform_machine != \"s390x\" and sys_platform == \"linux\""
+files = [
+ {file = "jeepney-0.9.0-py3-none-any.whl", hash = "sha256:97e5714520c16fc0a45695e5365a2e11b81ea79bba796e26f9f1d178cb182683"},
+ {file = "jeepney-0.9.0.tar.gz", hash = "sha256:cf0e9e845622b81e4a28df94c40345400256ec608d0e55bb8a3feaa9163f5732"},
+]
+
+[package.extras]
+test = ["async-timeout ; python_version < \"3.11\"", "pytest", "pytest-asyncio (>=0.17)", "pytest-trio", "testpath", "trio"]
+trio = ["trio"]
+
[[package]]
name = "jieba"
version = "0.42.1"
@@ -3435,6 +3574,37 @@ files = [
[package.dependencies]
numpy = ">=1.14"
+[[package]]
+name = "keyring"
+version = "25.6.0"
+description = "Store and access your passwords safely."
+optional = false
+python-versions = ">=3.9"
+groups = ["dev"]
+markers = "platform_machine != \"ppc64le\" and platform_machine != \"s390x\""
+files = [
+ {file = "keyring-25.6.0-py3-none-any.whl", hash = "sha256:552a3f7af126ece7ed5c89753650eec89c7eaae8617d0aa4d9ad2b75111266bd"},
+ {file = "keyring-25.6.0.tar.gz", hash = "sha256:0b39998aa941431eb3d9b0d4b2460bc773b9df6fed7621c2dfb291a7e0187a66"},
+]
+
+[package.dependencies]
+importlib_metadata = {version = ">=4.11.4", markers = "python_version < \"3.12\""}
+"jaraco.classes" = "*"
+"jaraco.context" = "*"
+"jaraco.functools" = "*"
+jeepney = {version = ">=0.4.2", markers = "sys_platform == \"linux\""}
+pywin32-ctypes = {version = ">=0.2.0", markers = "sys_platform == \"win32\""}
+SecretStorage = {version = ">=3.2", markers = "sys_platform == \"linux\""}
+
+[package.extras]
+check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\""]
+completion = ["shtab (>=1.1.0)"]
+cover = ["pytest-cov"]
+doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
+enabler = ["pytest-enabler (>=2.2)"]
+test = ["pyfakefs", "pytest (>=6,!=8.1.*)"]
+type = ["pygobject-stubs", "pytest-mypy", "shtab", "types-pywin32"]
+
[[package]]
name = "kiwisolver"
version = "1.4.9"
@@ -4317,14 +4487,14 @@ testing = ["coverage", "pyyaml"]
name = "markdown-it-py"
version = "4.0.0"
description = "Python port of markdown-it. Markdown parsing, done right!"
-optional = true
+optional = false
python-versions = ">=3.10"
-groups = ["main"]
-markers = "extra == \"evaluation\""
+groups = ["main", "dev"]
files = [
{file = "markdown_it_py-4.0.0-py3-none-any.whl", hash = "sha256:87327c59b172c5011896038353a81343b6754500a08cd7a4973bb48c6d578147"},
{file = "markdown_it_py-4.0.0.tar.gz", hash = "sha256:cb0a2b4aa34f932c007117b194e945bd74e0ec24133ceb5bac59009cda1cb9f3"},
]
+markers = {main = "extra == \"evaluation\""}
[package.dependencies]
mdurl = ">=0.1,<1.0"
@@ -4593,14 +4763,14 @@ test = ["Faker (>=1.0.2)", "pytest (>=6.0.1)", "pytest-md-report (>=0.6.2)"]
name = "mdurl"
version = "0.1.2"
description = "Markdown URL utilities"
-optional = true
+optional = false
python-versions = ">=3.7"
-groups = ["main"]
-markers = "extra == \"evaluation\""
+groups = ["main", "dev"]
files = [
{file = "mdurl-0.1.2-py3-none-any.whl", hash = "sha256:84008a41e51615a49fc9966191ff91509e3c40b939176e643fd50a5c2196b8f8"},
{file = "mdurl-0.1.2.tar.gz", hash = "sha256:bb413d29f5eea38f31dd4754dd7377d4465116fb207585f97bf925588687c1ba"},
]
+markers = {main = "extra == \"evaluation\""}
[[package]]
name = "mediapy"
@@ -4737,14 +4907,14 @@ dev = ["absl-py", "pyink", "pylint (>=2.6.0)", "pytest", "pytest-xdist"]
name = "more-itertools"
version = "10.8.0"
description = "More routines for operating on iterables, beyond itertools"
-optional = true
+optional = false
python-versions = ">=3.9"
-groups = ["main"]
-markers = "extra == \"evaluation\""
+groups = ["main", "dev"]
files = [
{file = "more_itertools-10.8.0-py3-none-any.whl", hash = "sha256:52d4362373dcf7c52546bc4af9a86ee7c4579df9a8dc268be0a2f949d376cc9b"},
{file = "more_itertools-10.8.0.tar.gz", hash = "sha256:f638ddf8a1a0d134181275fb5d58b086ead7c6a72429ad725c67503f13ba30bd"},
]
+markers = {main = "extra == \"evaluation\"", dev = "platform_machine != \"ppc64le\" and platform_machine != \"s390x\""}
[[package]]
name = "mpmath"
@@ -5324,6 +5494,42 @@ extra = ["lxml (>=4.6)", "pydot (>=3.0.1)", "pygraphviz (>=1.14)", "sympy (>=1.1
test = ["pytest (>=7.2)", "pytest-cov (>=4.0)", "pytest-xdist (>=3.0)"]
test-extras = ["pytest-mpl", "pytest-randomly"]
+[[package]]
+name = "nh3"
+version = "0.3.0"
+description = "Python binding to Ammonia HTML sanitizer Rust crate"
+optional = false
+python-versions = ">=3.8"
+groups = ["dev"]
+files = [
+ {file = "nh3-0.3.0-cp313-cp313t-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:a537ece1bf513e5a88d8cff8a872e12fe8d0f42ef71dd15a5e7520fecd191bbb"},
+ {file = "nh3-0.3.0-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7c915060a2c8131bef6a29f78debc29ba40859b6dbe2362ef9e5fd44f11487c2"},
+ {file = "nh3-0.3.0-cp313-cp313t-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:ba0caa8aa184196daa6e574d997a33867d6d10234018012d35f86d46024a2a95"},
+ {file = "nh3-0.3.0-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:80fe20171c6da69c7978ecba33b638e951b85fb92059259edd285ff108b82a6d"},
+ {file = "nh3-0.3.0-cp313-cp313t-musllinux_1_2_armv7l.whl", hash = "sha256:e90883f9f85288f423c77b3f5a6f4486375636f25f793165112679a7b6363b35"},
+ {file = "nh3-0.3.0-cp313-cp313t-musllinux_1_2_i686.whl", hash = "sha256:0649464ac8eee018644aacbc103874ccbfac80e3035643c3acaab4287e36e7f5"},
+ {file = "nh3-0.3.0-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:1adeb1062a1c2974bc75b8d1ecb014c5fd4daf2df646bbe2831f7c23659793f9"},
+ {file = "nh3-0.3.0-cp313-cp313t-win32.whl", hash = "sha256:7275fdffaab10cc5801bf026e3c089d8de40a997afc9e41b981f7ac48c5aa7d5"},
+ {file = "nh3-0.3.0-cp313-cp313t-win_amd64.whl", hash = "sha256:423201bbdf3164a9e09aa01e540adbb94c9962cc177d5b1cbb385f5e1e79216e"},
+ {file = "nh3-0.3.0-cp313-cp313t-win_arm64.whl", hash = "sha256:16f8670201f7e8e0e05ed1a590eb84bfa51b01a69dd5caf1d3ea57733de6a52f"},
+ {file = "nh3-0.3.0-cp38-abi3-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:ec6cfdd2e0399cb79ba4dcffb2332b94d9696c52272ff9d48a630c5dca5e325a"},
+ {file = "nh3-0.3.0-cp38-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ce5e7185599f89b0e391e2f29cc12dc2e206167380cea49b33beda4891be2fe1"},
+ {file = "nh3-0.3.0-cp38-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:389d93d59b8214d51c400fb5b07866c2a4f79e4e14b071ad66c92184fec3a392"},
+ {file = "nh3-0.3.0-cp38-abi3-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:e9e6a7e4d38f7e8dda9edd1433af5170c597336c1a74b4693c5cb75ab2b30f2a"},
+ {file = "nh3-0.3.0-cp38-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:7852f038a054e0096dac12b8141191e02e93e0b4608c4b993ec7d4ffafea4e49"},
+ {file = "nh3-0.3.0-cp38-abi3-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:af5aa8127f62bbf03d68f67a956627b1bd0469703a35b3dad28d0c1195e6c7fb"},
+ {file = "nh3-0.3.0-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f416c35efee3e6a6c9ab7716d9e57aa0a49981be915963a82697952cba1353e1"},
+ {file = "nh3-0.3.0-cp38-abi3-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:37d3003d98dedca6cd762bf88f2e70b67f05100f6b949ffe540e189cc06887f9"},
+ {file = "nh3-0.3.0-cp38-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:634e34e6162e0408e14fb61d5e69dbaea32f59e847cfcfa41b66100a6b796f62"},
+ {file = "nh3-0.3.0-cp38-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:b0612ccf5de8a480cf08f047b08f9d3fecc12e63d2ee91769cb19d7290614c23"},
+ {file = "nh3-0.3.0-cp38-abi3-musllinux_1_2_i686.whl", hash = "sha256:c7a32a7f0d89f7d30cb8f4a84bdbd56d1eb88b78a2434534f62c71dac538c450"},
+ {file = "nh3-0.3.0-cp38-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:3f1b4f8a264a0c86ea01da0d0c390fe295ea0bcacc52c2103aca286f6884f518"},
+ {file = "nh3-0.3.0-cp38-abi3-win32.whl", hash = "sha256:6d68fa277b4a3cf04e5c4b84dd0c6149ff7d56c12b3e3fab304c525b850f613d"},
+ {file = "nh3-0.3.0-cp38-abi3-win_amd64.whl", hash = "sha256:bae63772408fd63ad836ec569a7c8f444dd32863d0c67f6e0b25ebbd606afa95"},
+ {file = "nh3-0.3.0-cp38-abi3-win_arm64.whl", hash = "sha256:d97d3efd61404af7e5721a0e74d81cdbfc6e5f97e11e731bb6d090e30a7b62b2"},
+ {file = "nh3-0.3.0.tar.gz", hash = "sha256:d8ba24cb31525492ea71b6aac11a4adac91d828aadeff7c4586541bf5dc34d2f"},
+]
+
[[package]]
name = "ninja"
version = "1.13.0"
@@ -6254,7 +6460,7 @@ version = "24.2"
description = "Core utilities for Python packages"
optional = false
python-versions = ">=3.8"
-groups = ["main", "test"]
+groups = ["main", "dev", "test"]
files = [
{file = "packaging-24.2-py3-none-any.whl", hash = "sha256:09abb1bccd265c01f4a3aa3f7a7db064b36514d2cba19a2f694fe6150451a759"},
{file = "packaging-24.2.tar.gz", hash = "sha256:c228a6dc5e932d346bc5739379109d49e8853dd8223571c7c5b55260edc0b97f"},
@@ -7214,14 +7420,14 @@ pybtex = ">=0.16"
name = "pycparser"
version = "2.23"
description = "C parser in Python"
-optional = true
+optional = false
python-versions = ">=3.8"
-groups = ["main"]
-markers = "extra == \"evaluation\" and implementation_name != \"PyPy\""
+groups = ["main", "dev"]
files = [
{file = "pycparser-2.23-py3-none-any.whl", hash = "sha256:e5c6e8d3fbad53479cab09ac03729e0a9faf2bee3db8208a550daf5af81a5934"},
{file = "pycparser-2.23.tar.gz", hash = "sha256:78816d4f24add8f10a06d6f05b4d424ad9e96cfebf68a4ddc99c65c0720d00c2"},
]
+markers = {main = "extra == \"evaluation\" and implementation_name != \"PyPy\"", dev = "platform_machine != \"ppc64le\" and platform_machine != \"s390x\" and sys_platform == \"linux\" and platform_python_implementation != \"PyPy\" and implementation_name != \"PyPy\""}
[[package]]
name = "pydantic"
@@ -7551,6 +7757,18 @@ files = [
[package.dependencies]
pypinyin = "*"
+[[package]]
+name = "pyproject-hooks"
+version = "1.2.0"
+description = "Wrappers to call pyproject.toml-based build backend hooks."
+optional = false
+python-versions = ">=3.7"
+groups = ["dev"]
+files = [
+ {file = "pyproject_hooks-1.2.0-py3-none-any.whl", hash = "sha256:9e5c6bfa8dcc30091c74b0cf803c81fdd29d94f01992a7707bc97babb1141913"},
+ {file = "pyproject_hooks-1.2.0.tar.gz", hash = "sha256:1e859bd5c40fae9448642dd871adf459e5e2084186e8d2c2a79a824c970da1f8"},
+]
+
[[package]]
name = "pyre-extensions"
version = "0.0.32"
@@ -7823,6 +8041,19 @@ files = [
{file = "pywin32-311-cp39-cp39-win_arm64.whl", hash = "sha256:62ea666235135fee79bb154e695f3ff67370afefd71bd7fea7512fc70ef31e3d"},
]
+[[package]]
+name = "pywin32-ctypes"
+version = "0.2.3"
+description = "A (partial) reimplementation of pywin32 using ctypes/cffi"
+optional = false
+python-versions = ">=3.6"
+groups = ["dev"]
+markers = "platform_machine != \"ppc64le\" and platform_machine != \"s390x\" and sys_platform == \"win32\""
+files = [
+ {file = "pywin32-ctypes-0.2.3.tar.gz", hash = "sha256:d162dc04946d704503b2edc4d55f3dba5c1d539ead017afa00142c38b9885755"},
+ {file = "pywin32_ctypes-0.2.3-py3-none-any.whl", hash = "sha256:8a1513379d709975552d202d942d9837758905c8d01eb82b8bcc30918929e7b8"},
+]
+
[[package]]
name = "pyyaml"
version = "6.0.3"
@@ -8028,6 +8259,26 @@ files = [
[package.extras]
all = ["numpy"]
+[[package]]
+name = "readme-renderer"
+version = "44.0"
+description = "readme_renderer is a library for rendering readme descriptions for Warehouse"
+optional = false
+python-versions = ">=3.9"
+groups = ["dev"]
+files = [
+ {file = "readme_renderer-44.0-py3-none-any.whl", hash = "sha256:2fbca89b81a08526aadf1357a8c2ae889ec05fb03f5da67f9769c9a592166151"},
+ {file = "readme_renderer-44.0.tar.gz", hash = "sha256:8712034eabbfa6805cacf1402b4eeb2a73028f72d1166d6f5cb7f9c047c5d1e1"},
+]
+
+[package.dependencies]
+docutils = ">=0.21.2"
+nh3 = ">=0.2.14"
+Pygments = ">=2.5.1"
+
+[package.extras]
+md = ["cmarkgfm (>=0.8.0)"]
+
[[package]]
name = "referencing"
version = "0.36.2"
@@ -8154,14 +8405,14 @@ files = [
name = "requests"
version = "2.32.5"
description = "Python HTTP for Humans."
-optional = true
+optional = false
python-versions = ">=3.9"
-groups = ["main"]
-markers = "extra == \"evaluation\""
+groups = ["main", "dev"]
files = [
{file = "requests-2.32.5-py3-none-any.whl", hash = "sha256:2462f94637a34fd532264295e186976db0f5d453d1cdd31473c85a6a161affb6"},
{file = "requests-2.32.5.tar.gz", hash = "sha256:dbba0bac56e100853db0ea71b82b4dfd5fe2bf6d3754a8893c3af500cec7d7cf"},
]
+markers = {main = "extra == \"evaluation\""}
[package.dependencies]
certifi = ">=2017.4.17"
@@ -8174,6 +8425,21 @@ urllib3 = ">=1.21.1,<3"
socks = ["PySocks (>=1.5.6,!=1.5.7)"]
use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
+[[package]]
+name = "requests-toolbelt"
+version = "1.0.0"
+description = "A utility belt for advanced users of python-requests"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+groups = ["dev"]
+files = [
+ {file = "requests-toolbelt-1.0.0.tar.gz", hash = "sha256:7681a0a3d047012b5bdc0ee37d7f8f07ebe76ab08caeccfc3921ce23c88d5bc6"},
+ {file = "requests_toolbelt-1.0.0-py2.py3-none-any.whl", hash = "sha256:cccfdd665f0a24fcf4726e690f65639d272bb0637b9b92dfd91a5568ccf6bd06"},
+]
+
+[package.dependencies]
+requests = ">=2.0.1,<3.0.0"
+
[[package]]
name = "resampy"
version = "0.4.3"
@@ -8196,18 +8462,33 @@ design = ["optuna (>=2.10.0)"]
docs = ["numpydoc", "sphinx (!=1.3.1)"]
tests = ["pytest (<8)", "pytest-cov", "scipy (>=1.1)"]
+[[package]]
+name = "rfc3986"
+version = "2.0.0"
+description = "Validating URI References per RFC 3986"
+optional = false
+python-versions = ">=3.7"
+groups = ["dev"]
+files = [
+ {file = "rfc3986-2.0.0-py2.py3-none-any.whl", hash = "sha256:50b1502b60e289cb37883f3dfd34532b8873c7de9f49bb546641ce9cbd256ebd"},
+ {file = "rfc3986-2.0.0.tar.gz", hash = "sha256:97aacf9dbd4bfd829baad6e6309fa6573aaf1be3f6fa735c8ab05e46cecb261c"},
+]
+
+[package.extras]
+idna2008 = ["idna"]
+
[[package]]
name = "rich"
version = "14.1.0"
description = "Render rich text, tables, progress bars, syntax highlighting, markdown and more to the terminal"
-optional = true
+optional = false
python-versions = ">=3.8.0"
-groups = ["main"]
-markers = "extra == \"evaluation\""
+groups = ["main", "dev"]
files = [
{file = "rich-14.1.0-py3-none-any.whl", hash = "sha256:536f5f1785986d6dbdea3c75205c473f970777b4a0d6c6dd1b696aa05a3fa04f"},
{file = "rich-14.1.0.tar.gz", hash = "sha256:e497a48b844b0320d45007cdebfeaeed8db2a4f4bcf49f15e455cfc4af11eaa8"},
]
+markers = {main = "extra == \"evaluation\""}
[package.dependencies]
markdown-it-py = ">=2.2.0"
@@ -8813,6 +9094,23 @@ dev = ["flake8", "flit", "mypy", "pandas-stubs", "pre-commit", "pytest", "pytest
docs = ["ipykernel", "nbconvert", "numpydoc", "pydata_sphinx_theme (==0.10.0rc2)", "pyyaml", "sphinx (<6.0.0)", "sphinx-copybutton", "sphinx-design", "sphinx-issues"]
stats = ["scipy (>=1.7)", "statsmodels (>=0.12)"]
+[[package]]
+name = "secretstorage"
+version = "3.4.0"
+description = "Python bindings to FreeDesktop.org Secret Service API"
+optional = false
+python-versions = ">=3.10"
+groups = ["dev"]
+markers = "platform_machine != \"ppc64le\" and platform_machine != \"s390x\" and sys_platform == \"linux\""
+files = [
+ {file = "secretstorage-3.4.0-py3-none-any.whl", hash = "sha256:0e3b6265c2c63509fb7415717607e4b2c9ab767b7f344a57473b779ca13bd02e"},
+ {file = "secretstorage-3.4.0.tar.gz", hash = "sha256:c46e216d6815aff8a8a18706a2fbfd8d53fcbb0dce99301881687a1b0289ef7c"},
+]
+
+[package.dependencies]
+cryptography = ">=2.0"
+jeepney = ">=0.6"
+
[[package]]
name = "sentence-transformers"
version = "5.1.1"
@@ -10391,6 +10689,32 @@ build = ["cmake (>=3.20,<4.0)", "lit"]
tests = ["autopep8", "isort", "llnl-hatchet", "numpy", "pytest", "pytest-forked", "pytest-xdist", "scipy (>=1.7.1)"]
tutorials = ["matplotlib", "pandas", "tabulate"]
+[[package]]
+name = "twine"
+version = "6.2.0"
+description = "Collection of utilities for publishing packages on PyPI"
+optional = false
+python-versions = ">=3.9"
+groups = ["dev"]
+files = [
+ {file = "twine-6.2.0-py3-none-any.whl", hash = "sha256:418ebf08ccda9a8caaebe414433b0ba5e25eb5e4a927667122fbe8f829f985d8"},
+ {file = "twine-6.2.0.tar.gz", hash = "sha256:e5ed0d2fd70c9959770dce51c8f39c8945c574e18173a7b81802dab51b4b75cf"},
+]
+
+[package.dependencies]
+id = "*"
+keyring = {version = ">=21.2.0", markers = "platform_machine != \"ppc64le\" and platform_machine != \"s390x\""}
+packaging = ">=24.0"
+readme-renderer = ">=35.0"
+requests = ">=2.20"
+requests-toolbelt = ">=0.8.0,<0.9.0 || >0.9.0"
+rfc3986 = ">=1.4.0"
+rich = ">=12.0.0"
+urllib3 = ">=1.26.0"
+
+[package.extras]
+keyring = ["keyring (>=21.2.0)"]
+
[[package]]
name = "typeguard"
version = "4.4.4"
@@ -10523,14 +10847,14 @@ files = [
name = "urllib3"
version = "1.26.20"
description = "HTTP library with thread-safe connection pooling, file post, and more."
-optional = true
+optional = false
python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,>=2.7"
-groups = ["main"]
-markers = "extra == \"evaluation\""
+groups = ["main", "dev"]
files = [
{file = "urllib3-1.26.20-py2.py3-none-any.whl", hash = "sha256:0ed14ccfbf1c30a9072c7ca157e4319b70d65f623e91e7b32fadb2853431016e"},
{file = "urllib3-1.26.20.tar.gz", hash = "sha256:40c2dc0c681e47eb8f90e7e27bf6ff7df2e677421fd46756da1161c39ca70d32"},
]
+markers = {main = "extra == \"evaluation\""}
[package.extras]
brotli = ["brotli (==1.0.9) ; os_name != \"nt\" and python_version < \"3\" and platform_python_implementation == \"CPython\"", "brotli (>=1.0.9) ; python_version >= \"3\" and platform_python_implementation == \"CPython\"", "brotlicffi (>=0.8.0) ; (os_name != \"nt\" or python_version >= \"3\") and platform_python_implementation != \"CPython\"", "brotlipy (>=0.6.0) ; os_name == \"nt\" and python_version < \"3\""]
@@ -11231,14 +11555,14 @@ jupyter = ["ipytree (>=0.2.2)", "ipywidgets (>=8.0.0)", "notebook"]
name = "zipp"
version = "3.23.0"
description = "Backport of pathlib-compatible object wrapper for zip files"
-optional = true
+optional = false
python-versions = ">=3.9"
-groups = ["main"]
-markers = "extra == \"evaluation\""
+groups = ["main", "dev"]
files = [
{file = "zipp-3.23.0-py3-none-any.whl", hash = "sha256:071652d6115ed432f5ce1d34c336c0adfd6a884660d1e9712a256d3d3bd4b14e"},
{file = "zipp-3.23.0.tar.gz", hash = "sha256:a07157588a12518c9d4034df3fbbee09c814741a33ff63c05fa29d26a2404166"},
]
+markers = {main = "extra == \"evaluation\"", dev = "platform_machine != \"ppc64le\" and platform_machine != \"s390x\" and python_version == \"3.11\""}
[package.extras]
check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\""]
@@ -11367,4 +11691,4 @@ evaluation = ["backoff", "click", "datasets", "gitpython", "librosa", "matplotli
[metadata]
lock-version = "2.1"
python-versions = ">=3.11,<3.13"
-content-hash = "775241a8fc4d31e19ec076df20ff0b487a8a1550ab8b7a55937c87a5d00c02ed"
+content-hash = "e85d6750fd57aef24d768b31983780af4332306911fb4416e2525438574785b6"
diff --git a/pyproject.toml b/pyproject.toml
index 6a29296..8cc2d32 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -2,7 +2,21 @@
name = "error-align"
version = "0.1.0b1"
description = "Text-to-text alignment algorithm for speech recognition error analysis."
-authors = ["Lasse Borgholt"]
+authors = ["Lasse Borgholt "]
+license = "MIT"
+keywords = ["speech-recognition", "text-alignment", "NLP", "evaluation"]
+classifiers = [
+ "Programming Language :: Python :: 3",
+ "Programming Language :: Python :: 3.11",
+ "Programming Language :: Python :: 3.12",
+ "License :: OSI Approved :: MIT License",
+ "Operating System :: OS Independent",
+ "Topic :: Software Development :: Libraries",
+ "Topic :: Scientific/Engineering :: Artificial Intelligence",
+ "Topic :: Text Processing :: Linguistic",
+ "Intended Audience :: Developers",
+ "Intended Audience :: Science/Research",
+]
readme = "README.md"
packages = [
@@ -43,6 +57,8 @@ optional = true
ipython = "9.3.0"
ruff = ">=0.1,<0.13"
pre-commit = "^4.2.0"
+build = "^1.3.0"
+twine = "^6.2.0"
[tool.poetry.group.test]
optional = true
+ 
+ 
+ 
+ 
+