New model support for Speech Recognition
gitpqLee opened this issue · 0 comments
gitpqLee commented
Adds support for Speech Recognition network. Here are some model from open model zoo. You can pick anyone from those model or any other pose estimation model you are prefer
mozilla-deepspeech-0.6.1
quartznet-15x5-en
wav2vec2-base
The potential work should be:
- Add new sub-class as child of base input to parse the new input type for speech.
- Add new sub-class as child of [base Inference] (https://github.com/intel/ros2_openvino_toolkit/blob/master/openvino_wrapper_lib/include/openvino_wrapper_lib/inferences/base_inference.hpp) for Speech Recognition inference
- Add new sub-class as child of base model for Speech Recognition model parsing.
- Add new sub-class as child of base output to show the speech recognition results.
- [Optional] Create new ROS2 message type and update ros_topic_output and rviz_output