Phase 4 STT pipeline implemented — Silero VAD + faster-whisper — still not working well at all

This commit is contained in:
2026-01-17 03:14:40 +02:00
parent 3e59e5d2f6
commit d1e6b21508
30 changed files with 156595 additions and 8 deletions

35
stt/Dockerfile.stt Normal file
View File

@@ -0,0 +1,35 @@
FROM nvidia/cuda:12.1.0-base-ubuntu22.04
# Set working directory
WORKDIR /app
# Install system dependencies
RUN apt-get update && apt-get install -y \
python3.11 \
python3-pip \
ffmpeg \
libsndfile1 \
&& rm -rf /var/lib/apt/lists/*
# Copy requirements
COPY requirements.txt .
# Install Python dependencies
RUN pip3 install --no-cache-dir -r requirements.txt
# Copy application code
COPY . .
# Create models directory
RUN mkdir -p /models
# Expose port
EXPOSE 8000
# Set environment variables
ENV PYTHONUNBUFFERED=1
ENV CUDA_VISIBLE_DEVICES=0
ENV LD_LIBRARY_PATH=/usr/local/lib/python3.11/dist-packages/nvidia/cudnn/lib:${LD_LIBRARY_PATH}
# Run the server
CMD ["uvicorn", "stt_server:app", "--host", "0.0.0.0", "--port", "8000", "--log-level", "info"]