speech

ros_web_api_bellande_speech_detection/CMakeLists.txt

@@ -39,13 +39,22 @@ if($ENV{ROS_VERSION} EQUAL 1)
   )
 endif()
 
+# Install Python scripts for both ROS 1
+if($ENV{ROS_VERSION} EQUAL 1)
+  catkin_install_python(
+    PROGRAMS
+    src/bellande_speech_detection.py
+    DESTINATION ${CATKIN_PACKAGE_BIN_DESTINATION}
+  )
+endif()
+
 # Install Python scripts, configuration files, and launch files
 if($ENV{ROS_VERSION} EQUAL "1")
-    install(PROGRAMS src/bellande_2d_computer_vision_api_2d.py DESTINATION ${CATKIN_PACKAGE_LIB_DESTINATION})
+    install(PROGRAMS src/bellande_speech_detection.py DESTINATION ${CATKIN_PACKAGE_LIB_DESTINATION})
     install(DIRECTORY config/ DESTINATION ${CATKIN_PACKAGE_SHARE_DESTINATION}/config)
     install(DIRECTORY launch/ DESTINATION ${CATKIN_PACKAGE_SHARE_DESTINATION}/launch)
 elseif($ENV{ROS_VERSION} EQUAL "2")
-    install(PROGRAMS src/bellande_2d_computer_vision_api_2d.py DESTINATION lib/${PROJECT_NAME})
+    install(PROGRAMS src/bellande_speech_detection.py DESTINATION lib/${PROJECT_NAME})
     install(DIRECTORY config/ DESTINATION share/${PROJECT_NAME}/config)
     install(DIRECTORY launch/ DESTINATION share/${PROJECT_NAME}/launch)
 endif()

ros_web_api_bellande_speech_detection/config/configs.json

@@ -1,4 +1,20 @@
 {
+  "license": [
+    "Copyright (C) 2024 Bellande Robotics Sensors Research Innovation Center, Ronaldson Bellande",
+    "This program is free software: you can redistribute it and/or modify",
+    "it under the terms of the GNU General Public License as published by",
+    "the Free Software Foundation, either version 3 of the License, or",
+    "(at your option) any later version.",
+    "",
+    "This program is distributed in the hope that it will be useful,",
+    "but WITHOUT ANY WARRANTY; without even the implied warranty of",
+    "MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the",
+    "GNU General Public License for more details.",
+    "",
+    "You should have received a copy of the GNU General Public License",
+    "along with this program.  If not, see <https://www.gnu.org/licenses/>.",
+    "GNU General Public License v3.0 or later"
+  ],
   "url": "https://bellanderoboticssensorsresearchinnovationcenter-kot42qxp.b4a.run",
   "endpoint_path": {
     "prediction": "/api/Bellande_Speech_Detection/bellande_prediction",

ros_web_api_bellande_speech_detection/launch/bellande_speech_detection.launch.py

@@ -0,0 +1,71 @@
+# Copyright (C) 2024 Bellande Robotics Sensors Research Innovation Center, Ronaldson Bellande
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+import os
+import sys
+import subprocess
+from launch import LaunchDescription
+from launch_ros.actions import Node
+from launch.actions import DeclareLaunchArgument
+from launch.substitutions import LaunchConfiguration
+
+
+def ros1_launch_description():
+    # Get command-line arguments
+    args = sys.argv[1:]
+    # Construct the ROS 1 launch command
+    roslaunch_command = ["roslaunch", "ros_web_api_bellande_speech_detection", "bellande_speech_detection.launch"] + args
+    # Execute the launch command
+    subprocess.call(roslaunch_command)
+
+
+def ros2_launch_description():
+    # Declare launch arguments
+    audio_data_arg = DeclareLaunchArgument('audio_data')
+    sample_rate_arg = DeclareLaunchArgument('sample_rate')
+    language_arg = DeclareLaunchArgument('language')
+
+    # Create a list to hold all nodes to be launched
+    nodes_to_launch = []
+
+    # ROS2 specific configurations
+    ros_launch_arguments = [
+        audio_data_arg, sample_rate_arg, language_arg,
+    ]
+
+    nodes_to_launch.append(Node(
+        package='ros_web_api_bellande_speech_detection',
+        executable='bellande_speech_detection.py',
+        name='bellande_speech_detection_node',
+        output='screen',
+        parameters=[
+            {'audio_data': LaunchConfiguration('audio_data')},
+            {'sample_rate': LaunchConfiguration('sample_rate')},
+            {'language': LaunchConfiguration('language')},
+        ],
+    ))
+
+    # Return the LaunchDescription containing all nodes and arguments
+    return LaunchDescription(ros_launch_arguments + nodes_to_launch)
+
+if __name__ == "__main__":
+    ros_version = os.getenv("ROS_VERSION")
+    if ros_version == "1":
+        ros1_launch_description()
+    elif ros_version == "2":
+        ros2_launch_description()
+    else:
+        print("Unsupported ROS version. Please set the ROS_VERSION environment variable to '1' for ROS 1 or '2' for ROS 2.")
+        sys.exit(1)

ros_web_api_bellande_speech_detection/launch/ros1/bellande_speech_detection.launch

@@ -0,0 +1,30 @@
+<?xml version="1.0"?>
+<!--
+Copyright (C) 2024 Bellande Robotics Sensors Research Innovation Center, Ronaldson Bellande
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not
+use this file except in compliance with the License. You may obtain a copy of
+the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
+WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
+License for the specific language governing permissions and limitations under
+the License.
+-->
+<launch>
+  <!-- Define arguments -->
+  <arg name="audio_data" default="" />
+  <arg name="sample_rate" default="16000" />
+  <arg name="language" default="en-US" />
+
+  <!-- Launch the speech detection node -->
+  <node name="bellande_speech_detection_node" pkg="ros_web_api_bellande_speech_detection"
+    type="bellande_speech_detection.py" output="screen">
+    <param name="audio_data" value="$(arg audio_data)" />
+    <param name="sample_rate" value="$(arg sample_rate)" />
+    <param name="language" value="$(arg language)" />
+  </node>
+</launch>

ros_web_api_bellande_speech_detection/setup.py

@@ -0,0 +1,11 @@
+from distutils.core import setup
+from catkin_pkg.python_setup import generate_distutils_setup
+
+# fetch values from package.xml
+setup_args = generate_distutils_setup(
+    scripts=['src/bellande_speech_detection.py'],
+    packages=['ros_web_api_bellande_speech_detection'],
+    package_dir={'': 'src'},
+)
+
+setup(**setup_args)

ros_web_api_bellande_speech_detection/src/bellande_speech_detection.py

@@ -0,0 +1,73 @@
+# Copyright (C) 2024 Bellande Robotics Sensors Research Innovation Center, Ronaldson Bellande
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+import json
+import os
+import requests
+
+def main():
+    # Get the absolute path to the config file
+    config_file_path = os.path.join(os.path.dirname(__file__), '../config/configs.json')
+    
+    # Check if the config file exists
+    if not os.path.exists(config_file_path):
+        print("Config file not found:", config_file_path)
+        return
+
+    # Read configuration from config.json
+    with open(config_file_path, 'r') as config_file:
+        config = json.load(config_file)
+        url = config['url']
+        endpoint_path = config['endpoint_path']["detection"]
+    
+    # Get the parameters from the ROS parameter server
+    audio_data = rospy.get_param('audio_data', '')
+    sample_rate = rospy.get_param('sample_rate', 16000)
+    language = rospy.get_param('language', 'en-US')
+
+    # JSON payload
+    payload = {
+        "audio_data": audio_data,
+        "sample_rate": sample_rate,
+        "language": language
+    }
+
+    # Headers
+    headers = {
+        'accept': 'application/json',
+        'Content-Type': 'application/json'
+    }
+
+    # Make POST request
+    try:
+        response = requests.post(
+            url + endpoint_path,
+            json=payload,
+            headers=headers
+        )
+        response.raise_for_status()  # Raise an error for unsuccessful responses
+        data = response.json()
+        print("Detected Speech:", data['detected_speech'])
+    
+    except requests.exceptions.RequestException as e:
+        print("Error:", e)
+
+if __name__ == '__main__':
+    ros_version = os.getenv("ROS_VERSION")
+    if ros_version == "1":
+        import rospy
+    elif ros_version == "2":
+        import rclpy
+    main()