From ae8e9e189f5440ce6dfeb4700eb4234f499400e6 Mon Sep 17 00:00:00 2001
From: m-barker <mattbarker322@gmail.com>
Date: Mon, 29 Jan 2024 10:47:26 +0000
Subject: [PATCH] feat: tiago repeat after me demo script

---
 .../CMakeLists.txt                            |  1 +
 .../scripts/repeat_after_me.py                | 58 +++++++++++++++++++
 2 files changed, 59 insertions(+)
 create mode 100644 common/speech/lasr_speech_recognition_whisper/scripts/repeat_after_me.py

diff --git a/common/speech/lasr_speech_recognition_whisper/CMakeLists.txt b/common/speech/lasr_speech_recognition_whisper/CMakeLists.txt
index 75240eddb..9c2fe1f57 100644
--- a/common/speech/lasr_speech_recognition_whisper/CMakeLists.txt
+++ b/common/speech/lasr_speech_recognition_whisper/CMakeLists.txt
@@ -170,6 +170,7 @@ catkin_install_python(PROGRAMS
   nodes/transcribe_microphone_server
   scripts/list_microphones.py
   scripts/test_microphones.py
+  scripts/repeat_after_me.py
   DESTINATION ${CATKIN_PACKAGE_BIN_DESTINATION}
 )
 
diff --git a/common/speech/lasr_speech_recognition_whisper/scripts/repeat_after_me.py b/common/speech/lasr_speech_recognition_whisper/scripts/repeat_after_me.py
new file mode 100644
index 000000000..2e6b20622
--- /dev/null
+++ b/common/speech/lasr_speech_recognition_whisper/scripts/repeat_after_me.py
@@ -0,0 +1,58 @@
+#!/usr/bin/env python3
+import rospy
+import actionlib
+from lasr_voice import Voice  # type: ignore
+from lasr_speech_recognition_msgs.srv import TranscribeAudio, TranscribeAudioResponse  # type: ignore
+from lasr_speech_recognition_msgs.msg import (  # type: ignore
+    TranscribeSpeechAction,
+    TranscribeSpeechGoal,
+)
+
+# import actionlib
+rospy.init_node("repeat")
+
+USE_ACTIONLIB = True
+
+voice = Voice()
+
+
+if USE_ACTIONLIB:
+    client = actionlib.SimpleActionClient("transcribe_speech", TranscribeSpeechAction)
+    client.wait_for_server()
+    repeating = False
+    rospy.loginfo("Done waiting")
+    while not rospy.is_shutdown():
+        goal = TranscribeSpeechGoal()
+        client.send_goal(goal)
+        client.wait_for_result()
+        result = client.get_result()
+        text = result.sequence
+        print(text)
+        if "tiago" in text.lower().strip():
+            if "repeat" in text.lower().strip():
+                repeating = True
+                voice.sync_tts("Okay, I'll start repeating now.")
+                continue
+            elif "stop" in text.lower().strip():
+                repeating = False
+                voice.sync_tts("Okay, I'll stop repeating now.")
+                break
+        if repeating:
+            voice.sync_tts(f"I heard {text}")
+else:
+    transcribe = rospy.ServiceProxy("/whisper/transcribe_audio", TranscribeAudio)
+    repeating = False
+    while not rospy.is_shutdown():
+        text = transcribe().phrase
+        print(text)
+        if "tiago" in text.lower().strip():
+            if "repeat" in text.lower().strip():
+                repeating = True
+                voice.sync_tts("Okay, I'll start repeating now.")
+                continue
+            elif "stop" in text.lower().strip():
+                repeating = False
+                voice.sync_tts("Okay, I'll stop repeating now.")
+                break
+        if repeating:
+            voice.sync_tts(f"I heard {text}")