initial commit

.dockerignore

@@ -0,0 +1,142 @@
+.git
+Dockerfile
+.DS_Store
+.gitignore
+.dockerignore
+
+/credentials
+/cache
+/store
+
+/node_modules
+
+# https://github.com/github/gitignore/blob/master/Global/macOS.gitignore
+
+# General
+*.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+# https://raw.githubusercontent.com/github/gitignore/master/Python.gitignore
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# 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/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/

.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

@@ -0,0 +1,20 @@
+FROM python:3.10-slim
+
+WORKDIR /app
+
+COPY requirements.txt /app
+RUN apt-get update && apt-get install git -y
+RUN pip3 install -r requirements.txt
+RUN pip3 install "git+https://github.com/openai/whisper.git" 
+RUN apt-get install -y ffmpeg
+
+RUN whisper --model medium --language ru dummy.wav; exit 0
+RUN whisper --model small --language ru dummy.wav; exit 0
+
+COPY . .
+
+EXPOSE 5000
+
+ENV FLASK_APP=src/app.py
+
+CMD [ "python3", "-m" , "flask", "run", "--host=0.0.0.0"]

docker-compose.yaml

@@ -0,0 +1,10 @@
+version: '2.1'
+services:
+  harpyia:
+    container_name: harpyia
+    image: harpyia
+    build: .
+    ports:
+     - "8080:5000"
+    volumes:
+      - "./src:/app/src"

requirements.txt

@@ -0,0 +1,8 @@
+flask==3.0.2
+Jinja2==3.1.3
+blinker==1.7.0
+Werkzeug==3.0.1
+click==8.1.7
+itsdangerous==2.1.2
+MarkupSafe==2.1.5
+python-dotenv==1.0.1

src/app.py

@@ -0,0 +1,67 @@
+from flask import Flask, abort, request
+from tempfile import NamedTemporaryFile
+from dotenv import load_dotenv
+import os
+import whisper
+import torch
+import sys
+import re
+
+load_dotenv()
+
+HARPYIA_PROMPT = os.getenv('HARPYIA_PROMPT') or 'спасите помогите на помощь пожар'
+HARPYIA_MODEL = os.getenv('HARPYIA_MODEL') or 'medium'
+HARPYIA_LANGUAGE = os.getenv('HARPYIA_LANGUAGE') or 'ru'
+
+# Check if NVIDIA GPU is available
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+
+# Load the Whisper model:
+model = whisper.load_model(HARPYIA_MODEL, device=DEVICE)
+
+app = Flask(__name__)
+
+@app.route("/")
+def hello():
+    return "To recognize an audio file, upload it using a POST request with '/recognize' or '/recognize_number' route."
+
+def recognize_files(handler_fn):
+    if not request.files:
+        abort(400)
+
+    results = []
+
+    for filename, handle in request.files.items():
+        temp = NamedTemporaryFile()
+        handle.save(temp)
+        result = model.transcribe(temp.name, language=HARPYIA_LANGUAGE, initial_prompt=HARPYIA_PROMPT)
+        results.append({
+            'filename': filename,
+            'transcript': handler_fn(result['text']),
+        })
+
+    print(results, file=sys.stderr)
+    return {'results': results}
+
+@app.route('/recognize', methods=['POST'])
+def recognize():
+    return recognize_files(lambda text: text)
+
+@app.route('/recognize_number', methods=['POST'])
+def recognize_number():
+    return recognize_files(transfer_and_clean)
+
+def transfer_and_clean(input_string):
+    number_mapping = {
+        "один": "1",
+        "два": "2",
+        "три": "3"
+    }
+
+    for word, number in number_mapping.items():
+        input_string = input_string.replace(word, number)
+    
+    input_string = re.sub(r'[^\d]+', '', input_string)
+    
+    return input_string
+