Initial commit

Author: Security Level 5

.env.example

@@ -0,0 +1,28 @@
+# Secure Speech-to-Text - Configuration
+# Copy this file to .env and update with your settings
+
+# =============================================================================
+# Hugging Face Token (REQUIRED for speaker diarization)
+# =============================================================================
+# Get your token at: https://huggingface.co/settings/tokens
+# You must also accept the model conditions at:
+#   - https://huggingface.co/pyannote/speaker-diarization-3.1
+#   - https://huggingface.co/pyannote/segmentation-3.0
+HUGGINGFACE_HUB_TOKEN=your_token_here
+
+# =============================================================================
+# LLM API Configuration (for executive summaries)
+# =============================================================================
+# OpenAI-compatible API endpoint
+# Examples:
+#   LM Studio:  http://localhost:1234/v1
+#   Ollama:     http://localhost:11434/v1
+#   vLLM:       http://localhost:8000/v1
+API_BASE_URL=http://localhost:1234/v1
+
+# API key (use any value for local servers that don't require auth)
+API_KEY=lm-studio
+
+# Model name to use for executive summary generation
+# Use the model name as it appears in your local LLM server
+MODEL_NAME=local-model

.gitignore

@@ -0,0 +1,22 @@
+*.json
+*.tsv
+recording.txt
+*.vtt
+*.pdf
+executive_summary.md
+*.srt
+*.wav
+*.zip
+*.txt
+!requirements.txt
+*.m4a
+
+# Input/Output folders (keep folders, ignore contents)
+input/*
+!input/.gitkeep
+output/*
+!output/.gitkeep
+
+# Environment configuration
+.env
+.venv

Dockerfile

@@ -0,0 +1,50 @@
+# Secure Speech-to-Text - GPU Dockerfile (CUDA 12.8 + cuDNN)
+FROM nvidia/cuda:12.8.0-cudnn-runtime-ubuntu22.04
+
+# Prevent interactive prompts during package installation
+ENV DEBIAN_FRONTEND=noninteractive
+
+# Fix PyTorch 2.6+ weights_only default change (pyannote models need this)
+ENV TORCH_FORCE_NO_WEIGHTS_ONLY_LOAD=1
+
+# Install Python 3.13 and system dependencies
+RUN apt-get update && apt-get install -y \
+    software-properties-common \
+    && add-apt-repository ppa:deadsnakes/ppa \
+    && apt-get update && apt-get install -y \
+    python3.13 \
+    python3.13-venv \
+    python3.13-dev \
+    python3-pip \
+    ffmpeg \
+    git \
+    && rm -rf /var/lib/apt/lists/*
+
+# Set Python 3.13 as default
+RUN update-alternatives --install /usr/bin/python python /usr/bin/python3.13 1 \
+    && update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.13 1
+
+# Bootstrap pip for Python 3.13 (distutils removed in 3.12+)
+RUN python -m ensurepip --upgrade \
+    && python -m pip install --upgrade pip
+
+# Set working directory
+WORKDIR /app
+
+# Copy requirements and install dependencies (whisperx handles PyTorch)
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Ensure cuDNN from pip is on the library path (needed for torch 2.8 + cuDNN 9.x)
+ENV LD_LIBRARY_PATH=/usr/local/lib/python3.13/dist-packages/nvidia/cudnn/lib:$LD_LIBRARY_PATH
+
+# Copy application code
+COPY . .
+
+# Create input/output directories
+RUN mkdir -p input output
+
+# Set default command
+ENTRYPOINT ["python", "secure_speech_to_text.py"]
+CMD ["--help"]
+

Dockerfile.cpu

@@ -0,0 +1,38 @@
+# Secure Speech-to-Text - CPU Dockerfile
+FROM python:3.13-slim
+
+# Prevent interactive prompts during package installation
+ENV DEBIAN_FRONTEND=noninteractive
+
+# Fix PyTorch 2.6+ weights_only default change (pyannote models need this)
+ENV TORCH_FORCE_NO_WEIGHTS_ONLY_LOAD=1
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    ffmpeg \
+    git \
+    && rm -rf /var/lib/apt/lists/*
+
+# Bootstrap pip (ensurepip needed for 3.13) and install uv (fast parallel installer)
+RUN python -m ensurepip --upgrade \
+    && python -m pip install --upgrade pip \
+    && python -m pip install uv
+
+# Set working directory
+WORKDIR /app
+
+# Copy requirements and install dependencies using uv (fast, parallel downloads)
+COPY requirements.txt .
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv pip install --system --no-cache -r requirements.txt
+
+# Copy application code
+COPY . .
+
+# Create input/output directories
+RUN mkdir -p input output
+
+# Set default command
+ENTRYPOINT ["python", "secure_speech_to_text.py"]
+CMD ["--help"]
+

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Security Level 5
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.