a.pourmand commited on
Commit
76dce3d
1 Parent(s): b8ee1e0
Files changed (5) hide show
  1. .gitignore +160 -0
  2. Dockerfile +10 -3
  3. app.py +40 -1
  4. docker-compose.yaml +11 -2
  5. requirements.txt +1 -0
.gitignore ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Byte-compiled / optimized / DLL files
2
+ __pycache__/
3
+ *.py[cod]
4
+ *$py.class
5
+
6
+ # C extensions
7
+ *.so
8
+
9
+ # Distribution / packaging
10
+ .Python
11
+ build/
12
+ develop-eggs/
13
+ dist/
14
+ downloads/
15
+ eggs/
16
+ .eggs/
17
+ lib/
18
+ lib64/
19
+ parts/
20
+ sdist/
21
+ var/
22
+ wheels/
23
+ share/python-wheels/
24
+ *.egg-info/
25
+ .installed.cfg
26
+ *.egg
27
+ MANIFEST
28
+
29
+ # PyInstaller
30
+ # Usually these files are written by a python script from a template
31
+ # before PyInstaller builds the exe, so as to inject date/other infos into it.
32
+ *.manifest
33
+ *.spec
34
+
35
+ # Installer logs
36
+ pip-log.txt
37
+ pip-delete-this-directory.txt
38
+
39
+ # Unit test / coverage reports
40
+ htmlcov/
41
+ .tox/
42
+ .nox/
43
+ .coverage
44
+ .coverage.*
45
+ .cache
46
+ nosetests.xml
47
+ coverage.xml
48
+ *.cover
49
+ *.py,cover
50
+ .hypothesis/
51
+ .pytest_cache/
52
+ cover/
53
+
54
+ # Translations
55
+ *.mo
56
+ *.pot
57
+
58
+ # Django stuff:
59
+ *.log
60
+ local_settings.py
61
+ db.sqlite3
62
+ db.sqlite3-journal
63
+
64
+ # Flask stuff:
65
+ instance/
66
+ .webassets-cache
67
+
68
+ # Scrapy stuff:
69
+ .scrapy
70
+
71
+ # Sphinx documentation
72
+ docs/_build/
73
+
74
+ # PyBuilder
75
+ .pybuilder/
76
+ target/
77
+
78
+ # Jupyter Notebook
79
+ .ipynb_checkpoints
80
+
81
+ # IPython
82
+ profile_default/
83
+ ipython_config.py
84
+
85
+ # pyenv
86
+ # For a library or package, you might want to ignore these files since the code is
87
+ # intended to run in multiple environments; otherwise, check them in:
88
+ # .python-version
89
+
90
+ # pipenv
91
+ # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
92
+ # However, in case of collaboration, if having platform-specific dependencies or dependencies
93
+ # having no cross-platform support, pipenv may install dependencies that don't work, or not
94
+ # install all needed dependencies.
95
+ #Pipfile.lock
96
+
97
+ # poetry
98
+ # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
99
+ # This is especially recommended for binary packages to ensure reproducibility, and is more
100
+ # commonly ignored for libraries.
101
+ # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
102
+ #poetry.lock
103
+
104
+ # pdm
105
+ # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
106
+ #pdm.lock
107
+ # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
108
+ # in version control.
109
+ # https://pdm.fming.dev/#use-with-ide
110
+ .pdm.toml
111
+
112
+ # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
113
+ __pypackages__/
114
+
115
+ # Celery stuff
116
+ celerybeat-schedule
117
+ celerybeat.pid
118
+
119
+ # SageMath parsed files
120
+ *.sage.py
121
+
122
+ # Environments
123
+ .env
124
+ .venv
125
+ env/
126
+ venv/
127
+ ENV/
128
+ env.bak/
129
+ venv.bak/
130
+
131
+ # Spyder project settings
132
+ .spyderproject
133
+ .spyproject
134
+
135
+ # Rope project settings
136
+ .ropeproject
137
+
138
+ # mkdocs documentation
139
+ /site
140
+
141
+ # mypy
142
+ .mypy_cache/
143
+ .dmypy.json
144
+ dmypy.json
145
+
146
+ # Pyre type checker
147
+ .pyre/
148
+
149
+ # pytype static type analyzer
150
+ .pytype/
151
+
152
+ # Cython debug symbols
153
+ cython_debug/
154
+
155
+ # PyCharm
156
+ # JetBrains specific template is maintained in a separate JetBrains.gitignore that can
157
+ # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
158
+ # and can be added to the global gitignore or merged into this file. For a more nuclear
159
+ # option (not recommended) you can uncomment the following to ignore the entire idea folder.
160
+ #.idea/
Dockerfile CHANGED
@@ -1,12 +1,19 @@
1
  FROM python:3.9-slim
2
 
3
- COPY requirements.txt /tmp/requirements.txt
 
 
 
 
4
 
5
- WORKDIR /app
 
 
 
6
 
7
  RUN pip install --no-cache-dir -r /tmp/requirements.txt
8
 
9
- COPY . /app
10
 
11
  ENV PYTHONPATH=${HOME}/app \
12
  PYTHONUNBUFFERED=1 \
 
1
  FROM python:3.9-slim
2
 
3
+ RUN useradd -m -u 1000 user
4
+ USER user
5
+ ENV HOME=/home/user \
6
+ PATH=/home/user/.local/bin:${PATH}
7
+ WORKDIR ${HOME}/app
8
 
9
+ COPY --chown=1000 requirements.txt /tmp/requirements.txt
10
+
11
+ # install from develop branch
12
+ RUN pip install -qq https://github.com/pyannote/pyannote-audio/archive/refs/heads/develop.zip
13
 
14
  RUN pip install --no-cache-dir -r /tmp/requirements.txt
15
 
16
+ COPY --chown=1000 . ${HOME}/app
17
 
18
  ENV PYTHONPATH=${HOME}/app \
19
  PYTHONUNBUFFERED=1 \
app.py CHANGED
@@ -1,3 +1,42 @@
1
  import gradio as gr
 
 
2
 
3
- gr.Interface.load("models/pyannote/speaker-diarization").launch()
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  import gradio as gr
2
+ import os
3
+ from dotenv import load_dotenv
4
 
5
+ load_dotenv()
6
+
7
+ HF_API_KEY = os.getenv("HF_API_KEY")
8
+
9
+ # gr.Interface.load("models/pyannote/speaker-diarization").launch()
10
+
11
+ # 1. visit hf.co/pyannote/speaker-diarization and accept user conditions
12
+ # 2. visit hf.co/pyannote/segmentation and accept user conditions
13
+ # 3. visit hf.co/settings/tokens to create an access token
14
+ # 4. instantiate pretrained speaker diarization pipeline
15
+ from pyannote.audio import Pipeline
16
+
17
+ pipeline = Pipeline.from_pretrained(
18
+ "pyannote/speaker-diarization@2.1",
19
+ use_auth_token=HF_API_KEY,
20
+ )
21
+
22
+
23
+ def transcribe_audio(audio):
24
+ # Perform speech-to-text on audio file
25
+ # apply the pipeline to an audio file
26
+ diarization = pipeline(audio)
27
+ text = ""
28
+ for turn, _, speaker in diarization.itertracks(yield_label=True):
29
+ text = (
30
+ text
31
+ + f"start={turn.start:.1f}s stop={turn.end:.1f}s speaker_{speaker}"
32
+ + "\n"
33
+ )
34
+
35
+ return text
36
+
37
+
38
+ iface = gr.Interface(
39
+ fn=transcribe_audio, inputs=gr.Audio(source="upload"), outputs="text"
40
+ )
41
+
42
+ iface.launch()
docker-compose.yaml CHANGED
@@ -3,10 +3,19 @@ version: "3.7"
3
  services:
4
  pyannote_speaker_diarization:
5
  image: pyannote-speaker-diarization:v0.1
 
 
 
 
 
 
 
 
 
 
 
6
  build:
7
  context: .
8
  container_name: pyannote-speaker-diarization
9
- tty: true
10
- stdin_open: true
11
  ports:
12
  - 8007:9000
 
3
  services:
4
  pyannote_speaker_diarization:
5
  image: pyannote-speaker-diarization:v0.1
6
+ environment:
7
+ - GIT_PYTHON_REFRESH=quiet
8
+ - HUGGINGFACE_HUB_CACHE=/home/user/temp/.cache
9
+ - TRANSFORMERS_CACHE=/home/user/temp/.cache
10
+ - HF_HOME=/home/user/temp/.cache
11
+ - TORCH_HOME=/home/user/temp/torch
12
+ - TRANSFORMERS_OFFLINE=1
13
+ tty: true
14
+ stdin_open: true
15
+ volumes:
16
+ - ../torch/:/home/user/temp/torch
17
  build:
18
  context: .
19
  container_name: pyannote-speaker-diarization
 
 
20
  ports:
21
  - 8007:9000
requirements.txt CHANGED
@@ -1 +1,2 @@
1
  gradio==3.42.0
 
 
1
  gradio==3.42.0
2
+ python-dotenv==1.0.0