update

.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/

Dockerfile

@@ -1,12 +1,19 @@
 FROM python:3.9-slim
 
-COPY requirements.txt /tmp/requirements.txt
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:${PATH}
+WORKDIR ${HOME}/app
 
-WORKDIR /app
+COPY --chown=1000 requirements.txt /tmp/requirements.txt
+
+# install from develop branch
+RUN pip install -qq https://github.com/pyannote/pyannote-audio/archive/refs/heads/develop.zip
 
 RUN pip install --no-cache-dir -r /tmp/requirements.txt
 
-COPY . /app
+COPY --chown=1000 . ${HOME}/app
 
 ENV PYTHONPATH=${HOME}/app \
     PYTHONUNBUFFERED=1 \

app.py

@@ -1,3 +1,42 @@
 import gradio as gr
+import os
+from dotenv import load_dotenv
 
-gr.Interface.load("models/pyannote/speaker-diarization").launch()
+load_dotenv()
+
+HF_API_KEY = os.getenv("HF_API_KEY")
+
+# gr.Interface.load("models/pyannote/speaker-diarization").launch()
+
+# 1. visit hf.co/pyannote/speaker-diarization and accept user conditions
+# 2. visit hf.co/pyannote/segmentation and accept user conditions
+# 3. visit hf.co/settings/tokens to create an access token
+# 4. instantiate pretrained speaker diarization pipeline
+from pyannote.audio import Pipeline
+
+pipeline = Pipeline.from_pretrained(
+    "pyannote/speaker-diarization@2.1",
+    use_auth_token=HF_API_KEY,
+)
+
+
+def transcribe_audio(audio):
+    # Perform speech-to-text on audio file
+    # apply the pipeline to an audio file
+    diarization = pipeline(audio)
+    text = ""
+    for turn, _, speaker in diarization.itertracks(yield_label=True):
+        text = (
+            text
+            + f"start={turn.start:.1f}s stop={turn.end:.1f}s speaker_{speaker}"
+            + "\n"
+        )
+
+    return text
+
+
+iface = gr.Interface(
+    fn=transcribe_audio, inputs=gr.Audio(source="upload"), outputs="text"
+)
+
+iface.launch()

docker-compose.yaml

@@ -3,10 +3,19 @@ version: "3.7"
 services:
   pyannote_speaker_diarization:
     image: pyannote-speaker-diarization:v0.1
+    environment:
+      - GIT_PYTHON_REFRESH=quiet
+      - HUGGINGFACE_HUB_CACHE=/home/user/temp/.cache
+      - TRANSFORMERS_CACHE=/home/user/temp/.cache
+      - HF_HOME=/home/user/temp/.cache
+      - TORCH_HOME=/home/user/temp/torch
+      - TRANSFORMERS_OFFLINE=1
+    tty: true
+    stdin_open: true
+    volumes:
+      - ../torch/:/home/user/temp/torch
     build:
       context: .
     container_name: pyannote-speaker-diarization
-    tty: true
-    stdin_open: true
     ports:
       - 8007:9000

requirements.txt

@@ -1 +1,2 @@
 gradio==3.42.0
+python-dotenv==1.0.0