Speech Subtitle Generation on Jetson

.. In this project, we use the Riva ASR Server to capture data from the microphone input in real-time and display it on a webpage.

Requirement

• reComputer (Or other devices based on Jetson)
• reSpeaker (Or other USB interface microphones)
• Monitor, mouse, and keyboard

Prepare the runtime environment

1. Please refer to this wiki for installing Riva ASR Server.

2. Use the following command to install the runtime environment:

# flask
pip3 install flask
# riva client
git clone --depth=1 --recursive https://github.com/nvidia-riva/python-clients
cd python-clients
sudo pip3 install --upgrade pip setuptools wheel
pip3 install --no-cache-dir --verbose -r requirements.txt
python3 setup.py --verbose bdist_wheel
pip3 install --no-cache-dir --verbose dist/nvidia_riva_client*.whl
python3 -c 'import riva.client; print(riva.client.__version__)'
# pyaudio
sudo apt-get install -y --no-install-recommends python3-pyaudio

Let's run it！

git clone https://github.com/Seeed-Projects/Real-time-Subtitle-Recorder-on-Jetson.git
cd Real-time-Subtitle-Recorder-on-Jetson
python3 recorder.py

Run results

• https://youtu.be/XypO6BlXkCY?si=AuWyfqLKr5eYL_ez