Dockerfile implementation / Include Python Module syntax / README Update

.dockerignore

@@ -0,0 +1,89 @@
+# Git
+.git
+.gitignore
+.gitattributes
+
+
+# CI
+.codeclimate.yml
+.travis.yml
+.taskcluster.yml
+
+# Docker
+docker-compose.yml
+Dockerfile
+.docker
+.dockerignore
+
+# Byte-compiled / optimized / DLL files
+**/__pycache__/
+**/*.py[cod]
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.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
+.cache
+nosetests.xml
+coverage.xml
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Virtual environment
+.env
+.venv/
+venv/
+
+# PyCharm
+.idea
+
+# Python mode for VIM
+.ropeproject
+**/.ropeproject
+
+# Vim swap files
+**/*.swp
+
+# VS Code
+.vscode/

Dockerfile

@@ -0,0 +1,55 @@
+# -------------------------------------------------------
+# 1. Base image
+# -------------------------------------------------------
+FROM python:3.12-slim AS base
+
+# Prevent Python from writing .pyc files and using stdout buffering
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV PYTHONUNBUFFERED=1
+#additionally run export UV_HTTP_TIMEOUT=120 on local shell
+ENV UV_HTTP_TIMEOUT=300
+ENV PYTHONPATH="/app/src"
+
+
+
+# -------------------------------------------------------
+# 2. Install system dependencies
+# -------------------------------------------------------
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    ffmpeg \
+    && rm -rf /var/lib/apt/lists/*
+
+# -------------------------------------------------------
+# 3. Install uv (fast Python package manager)
+# -------------------------------------------------------
+RUN pip install --no-cache-dir uv
+
+# -------------------------------------------------------
+# 4. Copy project metadata first (layer caching)
+# -------------------------------------------------------
+WORKDIR /app
+COPY pyproject.toml uv.lock ./
+
+# -------------------------------------------------------
+# 5. Install dependencies using uv
+# -------------------------------------------------------
+RUN uv sync 
+#--no-dev
+
+# -------------------------------------------------------
+# 6. Copy the actual application
+# -------------------------------------------------------
+COPY src/ ./src/
+
+# -------------------------------------------------------
+# 7. Expose API port and run app
+# -------------------------------------------------------
+#It does not open the port or publish anything to your host.
+#Indicates to other developers that the container listens on port 8000.
+#Has no effect unless someone uses --expose or configures port mapping.
+#Flask app’s default port is 5000,
+EXPOSE 5000
+
+#CORRECT from root directory
+CMD ["uv", "run", "flask", "--app", "src.app.main", "run", "--host=0.0.0.0", "--port=5000"] 

README.md

@@ -56,19 +56,30 @@ This automatically:
 
 ------------------------------------------------------------------------
 
-## 🏃 3. Running the Transcription Script
+## 🏃 3. Running the Transcription Script and Flask API
 
 Run from the **root directory**:
 
 ``` bash
-uv run src/app/convertor/service/transcription_service.py   
+source .env
+uv run -m src.app.convertor.service.transcription
+```
+
+``` bash
+uv run flask --app src.app.main run --debug
 ```
 
 ### Important
 
 Running from the project root ensures that relative paths like
 `data/inputs/...` resolve correctly.
 
+The .env file contains the python path (PYTHONPATH):
+
+``` bash
+export PYTHONPATH=$(pwd)/src
+```
+ Which ensures the project root is in the PYTHONPATH, so  python can find the project modules. For this project "src"  should be treated as the root of the package.
 
 ## 🧪 5. Running Tests (if applicable)
 
@@ -95,6 +106,43 @@ uv sync
 
 ------------------------------------------------------------------------
 
+## 🚀   Docker
+
+
+1. Create an image from the Dockerfile
+
+``` bash
+docker build -t myflaskapp .
+```
+2. Create, start and attach a Docker Container
+
+``` bash
+docker run -t myflaskapp .
+```
+
+3. To access Flask from localhost
+
+Flask must listen on all interfaces, not just localhost, or it will be unreachable from your machine. The local cmd
+
+``` bash
+CMD ["uv", "run", "flask", "--app", "src.app.main", "run"] ❌ Required change: Add host
+CMD ["uv", "run", "flask", "--app", "src.app.main", "run", "--host=0.0.0.0", "--port=5000"]
+
+```
+
+Then run the container, and access Flask using Port Binding
+``` bash
+docker run --rm -p <host_port>:<conteiner_port> myflaskapp
+
+docker run --rm -p 5001:5000 myflaskapp
+``` 
+
+Now in the local browser we can access our running flask application at:
+
+[text](http://localhost:5004/)
+
+------------------------------------------------------------------------
+
 ## ❗ Troubleshooting
 
 ### **FileNotFoundError for audio inputs**
@@ -112,6 +160,4 @@ Incorrect:
 ``` bash
 cd src/app/convertor/service/
 uv run transcription_service.py   # ❌ breaks relative paths
-```
-
-------------------------------------------------------------------------
+```

pyproject.toml

@@ -15,3 +15,16 @@ dependencies = [
     "ruff>=0.14.6",
     "torch>=2.9.1",
 ]
+
+# Add the PyTorch CPU index as an additional index
+[[tool.uv.index]]
+name = "pytorch-cpu"
+url = "https://download.pytorch.org/whl/cpu"
+#recommend the use of explicit = true to ensure that the index is only used for torch
+explicit = true
+
+# Tell uv that ONLY torch should come from this index ->  To point torch to the desired index:
+[tool.uv.sources]
+torch = [
+    { index = "pytorch-cpu" }
+]

src/app/convertor/service/convertor_service.py

@@ -1,12 +1,13 @@
-from convertor.service.transcription import Transcription
+from app.convertor.service.transcription import Transcription
 
 
 class ConvertorService:
 
     @classmethod
     def create_text(cls):
         # data_dir = "data"
-        input_file_name = "./convertor/service/data/inputs/5846093734223028963.ogg"
+        input_file_name = "./src/app/convertor/service/data/inputs/5846093734223028963.ogg"
+        # input_file_name = "./convertor/service/data/inputs/5846093734223028963.ogg"
         # output_file_name = "./data/outputs/5846093734223028963"
         model_id = "tiny"
         show_text = True

src/app/convertor/service/transcription.py

@@ -98,6 +98,7 @@ def get_transcription(self):
 
         result = model.transcribe(
             self.input_file_name,
+            fp16=False
         )
 
         if self.show_text:

src/app/main.py

@@ -1,5 +1,5 @@
 from flask import Flask
-from convertor.service.convertor_service import ConvertorService
+from app.convertor.service.convertor_service import ConvertorService
 
 app = Flask(__name__)