Brummel
268954f722
This commit introduces a new standalone FastAPI service for the NVIDIA Canary ASR model. Key changes include: - A new `canary/` directory containing the service code. - `Dockerfile`: Defines the Docker image for the Canary service. - `docker-compose.yml`: Configures the Docker Compose setup for running the service. - `main.py`: Implements the FastAPI application, model loading, and inference logic. - `requirements.txt`: Lists the Python dependencies for the service. - `CHUNKING.md`: Documents the long-form audio handling strategy for Canary. - `README.md`: Provides an overview of the service, API, and deployment instructions. - `deploy.sh`: A script for deploying the service to a remote host. This service allows for independent evaluation and deployment of the Canary ASR model, separate from the existing `doctate-whisper` service. It utilizes a buffered inference approach for handling long audio files, as detailed in `CHUNKING.md`.
33 lines
731 B
Docker
33 lines
731 B
Docker
FROM nvidia/cuda:12.6.1-devel-ubuntu22.04
|
|
|
|
ENV DEBIAN_FRONTEND=noninteractive \
|
|
PIP_NO_CACHE_DIR=1 \
|
|
PYTHONDONTWRITEBYTECODE=1 \
|
|
PYTHONUNBUFFERED=1
|
|
|
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
python3 python3-pip python3-dev \
|
|
ffmpeg \
|
|
libsndfile1 \
|
|
git \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
WORKDIR /app
|
|
|
|
COPY requirements.txt .
|
|
RUN pip install --upgrade pip && \
|
|
pip install -r requirements.txt
|
|
|
|
COPY main.py .
|
|
|
|
ENV CANARY_MODEL=nvidia/canary-1b-v2 \
|
|
CANARY_DEVICE=cuda \
|
|
CANARY_PRECISION=bf16 \
|
|
CANARY_MODELS_DIR=/models \
|
|
HF_HOME=/models
|
|
|
|
VOLUME ["/models"]
|
|
EXPOSE 9002
|
|
|
|
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "9002", "--workers", "1"]
|