fix: impl handler

.gitattributes

@@ -24,4 +24,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
+*.wav filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

.python-version

@@ -0,0 +1 @@
+3.9.13

config.yaml

@@ -5,7 +5,7 @@ pipeline:
     embedding: speechbrain/spkrec-ecapa-voxceleb
     embedding_batch_size: 32
     embedding_exclude_overlap: true
-    segmentation: pyannote/segmentation@2022.07
+    segmentation: pyannote_segmentation_2022_07_pythorch_model.bin
     segmentation_batch_size: 32
 
 params:

handler.py

@@ -0,0 +1,41 @@
+from typing import Dict
+from pyannote.audio import Pipeline
+from io import BytesIO
+import torch
+import torchaudio
+
+
+class EndpointHandler:
+    def __init__(self, path=""):
+        # load the model
+        self.pipeline = Pipeline.from_pretrained("config.yaml")
+
+    def __call__(self, data: Dict[str, bytes]) -> Dict[str, str]:
+        """
+        Args:
+            data (:obj:):
+                includes the deserialized audio file as bytes
+        Return:
+            A :obj:`dict`:. base64 encoded image
+        """
+        # process input
+        inputs = data.pop("inputs", data)
+        parameters = data.pop("parameters", None)  #  min_speakers=2, max_speakers=5
+
+        waveform, sample_rate = torchaudio.load(BytesIO(inputs))
+        pyannote_input = {"waveform": waveform, "sample_rate": sample_rate}
+
+        # apply pretrained pipeline
+        # pass inputs with all kwargs in data
+        if parameters is not None:
+            diarization = self.pipeline(pyannote_input, **parameters)
+        else:
+            diarization = self.pipeline(pyannote_input)
+
+        # postprocess the prediction
+        processed_diarization = [
+            {"label": str(label), "start": str(segment.start), "stop": str(segment.end)}
+            for segment, _, label in diarization.itertracks(yield_label=True)
+        ]
+
+        return {"diarization": processed_diarization}

handler_test.py

@@ -0,0 +1,9 @@
+from handler import EndpointHandler
+from pathlib import Path
+
+my_handler = EndpointHandler()
+
+with open("./handler_test.wav", "rb") as file:
+    bytes_data = file.read()
+res = my_handler({"inputs": bytes_data})
+print(res)

handler_test.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:187386cda67317574da5b30068a8b853e52cc6df0d13abfec381912dfa9e7461
+size 1920062

pyannote_segmentation_2022_07_pythorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b5b3216d60a2d32fc086b47ea8c67589aaeb26b7e07fcbe620d6d0b83e209ea
+size 17719103

pyproject.toml

@@ -0,0 +1,25 @@
+[project]
+name = "pyannote-speaker-diarization"
+version = "0.1.0"
+description = "Add your description here"
+authors = [
+    { name = "Katsuya Oda", email = "katsuya@hicustomer.jp" }
+]
+dependencies = [
+    "pyannote.audio @ git+https://github.com/pyannote/pyannote-audio.git@2.1.1",
+    "torch==1.13.1",
+    "black>=23.7.0",
+]
+readme = "README.md"
+requires-python = ">= 3.8"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.rye]
+managed = true
+dev-dependencies = []
+
+[tool.hatch.metadata]
+allow-direct-references = true

requirements-dev.lock

@@ -0,0 +1,136 @@
+# generated by rye
+# use `rye lock` or `rye sync` to update this lockfile
+#
+# last locked with the following flags:
+#   pre: false
+#   features: []
+#   all-features: false
+
+-e file:.
+absl-py==1.4.0
+aiohttp==3.8.5
+aiosignal==1.3.1
+alembic==1.11.2
+antlr4-python3-runtime==4.9.3
+asteroid-filterbanks==0.4.0
+async-timeout==4.0.2
+attrs==23.1.0
+audioread==3.0.0
+backports-cached-property==1.0.2
+black==23.7.0
+cachetools==5.3.1
+certifi==2023.7.22
+cffi==1.15.1
+charset-normalizer==3.2.0
+click==8.1.6
+cmaes==0.10.0
+colorama==0.4.6
+colorlog==6.7.0
+contourpy==1.1.0
+cycler==0.11.0
+decorator==5.1.1
+docopt==0.6.2
+einops==0.3.2
+filelock==3.12.2
+fonttools==4.42.0
+frozenlist==1.4.0
+fsspec==2023.6.0
+google-auth==2.22.0
+google-auth-oauthlib==1.0.0
+greenlet==2.0.2
+grpcio==1.56.2
+hmmlearn==0.2.8
+huggingface-hub==0.16.4
+hyperpyyaml==1.2.1
+idna==3.4
+importlib-metadata==6.8.0
+importlib-resources==6.0.1
+joblib==1.3.1
+julius==0.2.7
+kiwisolver==1.4.4
+librosa==0.9.2
+llvmlite==0.40.1
+mako==1.2.4
+markdown==3.4.4
+markdown-it-py==3.0.0
+markupsafe==2.1.3
+matplotlib==3.7.2
+mdurl==0.1.2
+mpmath==1.3.0
+multidict==6.0.4
+mypy-extensions==1.0.0
+networkx==2.8.8
+numba==0.57.1
+numpy==1.24.4
+nvidia-cublas-cu11==11.10.3.66
+nvidia-cuda-nvrtc-cu11==11.7.99
+nvidia-cuda-runtime-cu11==11.7.99
+nvidia-cudnn-cu11==8.5.0.96
+oauthlib==3.2.2
+omegaconf==2.3.0
+optuna==3.3.0
+packaging==23.1
+pandas==2.0.3
+pathspec==0.11.2
+pillow==10.0.0
+platformdirs==3.10.0
+pooch==1.7.0
+primepy==1.3
+protobuf==3.20.1
+pyannote-audio @ git+https://github.com/pyannote/pyannote-audio.git@2.1.1
+pyannote-core==4.5
+pyannote-database==4.1.3
+pyannote-metrics==3.2.1
+pyannote-pipeline==2.3
+pyasn1==0.5.0
+pyasn1-modules==0.3.0
+pycparser==2.21
+pydeprecate==0.3.2
+pygments==2.16.1
+pyparsing==3.0.9
+python-dateutil==2.8.2
+pytorch-lightning==1.6.5
+pytorch-metric-learning==1.7.3
+pytz==2023.3
+pyyaml==6.0.1
+requests==2.31.0
+requests-oauthlib==1.3.1
+resampy==0.4.2
+rich==13.5.2
+rsa==4.9
+ruamel-yaml==0.17.28
+ruamel-yaml-clib==0.2.7
+scikit-learn==1.3.0
+scipy==1.11.1
+semver==2.13.0
+sentencepiece==0.1.99
+shellingham==1.5.0.post1
+simplejson==3.19.1
+singledispatchmethod==1.0
+six==1.16.0
+sortedcontainers==2.4.0
+soundfile==0.10.3.post1
+speechbrain==0.5.15
+sqlalchemy==2.0.19
+sympy==1.12
+tabulate==0.9.0
+tensorboard==2.13.0
+tensorboard-data-server==0.7.1
+threadpoolctl==3.2.0
+tomli==2.0.1
+torch==1.13.1
+torch-audiomentations==0.11.0
+torch-pitch-shift==1.2.4
+torchaudio==0.13.1
+torchmetrics==0.11.4
+tqdm==4.65.0
+typer==0.9.0
+typing-extensions==4.7.1
+tzdata==2023.3
+urllib3==1.26.16
+werkzeug==2.3.6
+wheel==0.41.1
+yarl==1.9.2
+zipp==3.16.2
+# The following packages are considered to be unsafe in a requirements file:
+setuptools==68.0.0

requirements.lock

@@ -0,0 +1,136 @@
+# generated by rye
+# use `rye lock` or `rye sync` to update this lockfile
+#
+# last locked with the following flags:
+#   pre: false
+#   features: []
+#   all-features: false
+
+-e file:.
+absl-py==1.4.0
+aiohttp==3.8.5
+aiosignal==1.3.1
+alembic==1.11.2
+antlr4-python3-runtime==4.9.3
+asteroid-filterbanks==0.4.0
+async-timeout==4.0.2
+attrs==23.1.0
+audioread==3.0.0
+backports-cached-property==1.0.2
+black==23.7.0
+cachetools==5.3.1
+certifi==2023.7.22
+cffi==1.15.1
+charset-normalizer==3.2.0
+click==8.1.6
+cmaes==0.10.0
+colorama==0.4.6
+colorlog==6.7.0
+contourpy==1.1.0
+cycler==0.11.0
+decorator==5.1.1
+docopt==0.6.2
+einops==0.3.2
+filelock==3.12.2
+fonttools==4.42.0
+frozenlist==1.4.0
+fsspec==2023.6.0
+google-auth==2.22.0
+google-auth-oauthlib==1.0.0
+greenlet==2.0.2
+grpcio==1.56.2
+hmmlearn==0.2.8
+huggingface-hub==0.16.4
+hyperpyyaml==1.2.1
+idna==3.4
+importlib-metadata==6.8.0
+importlib-resources==6.0.1
+joblib==1.3.1
+julius==0.2.7
+kiwisolver==1.4.4
+librosa==0.9.2
+llvmlite==0.40.1
+mako==1.2.4
+markdown==3.4.4
+markdown-it-py==3.0.0
+markupsafe==2.1.3
+matplotlib==3.7.2
+mdurl==0.1.2
+mpmath==1.3.0
+multidict==6.0.4
+mypy-extensions==1.0.0
+networkx==2.8.8
+numba==0.57.1
+numpy==1.24.4
+nvidia-cublas-cu11==11.10.3.66
+nvidia-cuda-nvrtc-cu11==11.7.99
+nvidia-cuda-runtime-cu11==11.7.99
+nvidia-cudnn-cu11==8.5.0.96
+oauthlib==3.2.2
+omegaconf==2.3.0
+optuna==3.3.0
+packaging==23.1
+pandas==2.0.3
+pathspec==0.11.2
+pillow==10.0.0
+platformdirs==3.10.0
+pooch==1.7.0
+primepy==1.3
+protobuf==3.20.1
+pyannote-audio @ git+https://github.com/pyannote/pyannote-audio.git@2.1.1
+pyannote-core==4.5
+pyannote-database==4.1.3
+pyannote-metrics==3.2.1
+pyannote-pipeline==2.3
+pyasn1==0.5.0
+pyasn1-modules==0.3.0
+pycparser==2.21
+pydeprecate==0.3.2
+pygments==2.16.1
+pyparsing==3.0.9
+python-dateutil==2.8.2
+pytorch-lightning==1.6.5
+pytorch-metric-learning==1.7.3
+pytz==2023.3
+pyyaml==6.0.1
+requests==2.31.0
+requests-oauthlib==1.3.1
+resampy==0.4.2
+rich==13.5.2
+rsa==4.9
+ruamel-yaml==0.17.28
+ruamel-yaml-clib==0.2.7
+scikit-learn==1.3.0
+scipy==1.11.1
+semver==2.13.0
+sentencepiece==0.1.99
+shellingham==1.5.0.post1
+simplejson==3.19.1
+singledispatchmethod==1.0
+six==1.16.0
+sortedcontainers==2.4.0
+soundfile==0.10.3.post1
+speechbrain==0.5.15
+sqlalchemy==2.0.19
+sympy==1.12
+tabulate==0.9.0
+tensorboard==2.13.0
+tensorboard-data-server==0.7.1
+threadpoolctl==3.2.0
+tomli==2.0.1
+torch==1.13.1
+torch-audiomentations==0.11.0
+torch-pitch-shift==1.2.4
+torchaudio==0.13.1
+torchmetrics==0.11.4
+tqdm==4.65.0
+typer==0.9.0
+typing-extensions==4.7.1
+tzdata==2023.3
+urllib3==1.26.16
+werkzeug==2.3.6
+wheel==0.41.1
+yarl==1.9.2
+zipp==3.16.2
+# The following packages are considered to be unsafe in a requirements file:
+setuptools==68.0.0

requirements.txt

@@ -0,0 +1,2 @@
+torch==1.13.1
+pyannote.audio @ git+https://github.com/pyannote/pyannote-audio.git@2.1.1