Development
Development Environment¶
Install poetry with following command:
pip3 install poetry
Installation¶
Install packages:
poetry install
Note
By default, this will install the CPU version of PyTorch. For GPU support, you'll need to install the appropriate CUDA version of PyTorch separately:
# For CUDA support (example for CUDA 11.8):
pip3 install torch==2.6.0 --index-url https://download.pytorch.org/whl/cu121
Run¶
Starting the Webservice:
poetry run whisper-asr-webservice --host 0.0.0.0 --port 9000
Build¶
With Dockerfile
:
# Build Image
docker build -t whisper-asr-webservice .
# Run Container
docker run -d -p 9000:9000 whisper-asr-webservice
# or with specific model
docker run -d -p 9000:9000 -e ASR_MODEL=base whisper-asr-webservice
# Build Image
docker build -f Dockerfile.gpu -t whisper-asr-webservice-gpu .
# Run Container
docker run -d --gpus all -p 9000:9000 whisper-asr-webservice-gpu
# or with specific model
docker run -d --gpus all -p 9000:9000 -e ASR_MODEL=base whisper-asr-webservice-gpu
With docker-compose
:
docker-compose up --build
docker-compose -f docker-compose.gpu.yml up --build
Build .whl package
poetry build