feat: save microphone output to audio files

.gitignore

@@ -133,4 +133,8 @@ common/Perception/face_detection/output/
 common/Perception/lasr_object_detection_yolo/models
 .vscode/
 common/navigation/choosing_wait_position/src/choosing_wait_position/final_lift_key_point/models
-legacy/choosing_wait_position/src/choosing_wait_position/final_lift_key_point/models/keypointsrcnn_weights.pth
+legacy/choosing_wait_position/src/choosing_wait_position/final_lift_key_point/models/keypointsrcnn_weights.pth
+
+# Python extension setup files
+.pylintrc
+mypy.ini

common/speech/lasr_speech_recognition_whisper/CMakeLists.txt

@@ -163,6 +163,7 @@ catkin_install_python(PROGRAMS
   nodes/simple_transcribe_microphone
   nodes/transcribe_microphone
   scripts/list_microphones.py
+  scripts/test_microphones.py
   DESTINATION ${CATKIN_PACKAGE_BIN_DESTINATION}
 )
 

common/speech/lasr_speech_recognition_whisper/scripts/test_microphones.py

@@ -0,0 +1,55 @@
+#!/usr/bin/env python3
+
+import os
+import argparse
+import speech_recognition as sr
+
+
+def parse_args() -> dict:
+    """Parse command line arguments into a dictionary.
+
+    Returns:
+        dict: name: value pairs of command line arguments
+    """
+
+    parser = argparse.ArgumentParser(description="Test microphones")
+    parser.add_argument("-m", "--microphone", type=int, help="Microphone index")
+    parser.add_argument(
+        "-o", "--output_dir", type=str, help="Directory to save audio files"
+    )
+
+    return vars(parser.parse_args())
+
+
+def main(args: dict) -> None:
+    """Generate audio files from microphone input.
+
+    Args:
+        args (dict): dictionary of command line arguments.
+    """
+
+    # Adapted from https://github.com/Uberi/speech_recognition/blob/master/examples/write_audio.py
+
+    mic_index = args["microphone"]
+    output_dir = args["output_dir"]
+
+    r = sr.Recognizer()
+    with sr.Microphone(device_index=mic_index) as source:
+        print("Say something!")
+        audio = r.listen(source)
+
+    with open(os.path.join(output_dir, "microphone.raw"), "wb") as f:
+        f.write(audio.get_raw_data())
+
+    with open(os.path.join(output_dir, "microphone.wav"), "wb") as f:
+        f.write(audio.get_wav_data())
+
+    with open(os.path.join(output_dir, "microphone.flac"), "wb") as f:
+        f.write(audio.get_flac_data())
+
+    with open(os.path.join(output_dir, "microphone.aiff"), "wb") as f:
+        f.write(audio.get_aiff_data())
+
+
+if __name__ == "__main__":
+    main(parse_args())