Added whisper node

8 files changed, 355 insertions, 7 deletions

diff --git a/.devcontainer/Dockerfile b/.devcontainer/Dockerfile
index 6992623..9bcb4d7 100644
--- a/.devcontainer/Dockerfile
+++ b/.devcontainer/Dockerfile
@@ -26,7 +26,7 @@ RUN sudo apt install -y git python3-pip
 # Rosdep update
 RUN rosdep update
 
-RUN pip3 install jinja2 ollama geocoder requests python-dotenv parsimonious
+RUN pip3 install jinja2 ollama geocoder requests python-dotenv parsimonious SpeechRecognition
 
 # Source the ROS setup file
 RUN echo "source /opt/ros/${ROS_DISTRO}/setup.bash" >> ~/.bashrc
diff --git a/noetic-llama/src/ollamamessages/CMakeLists.txt b/noetic-llama/src/ollamamessages/CMakeLists.txt
index b397131..7f1e55c 100644
--- a/noetic-llama/src/ollamamessages/CMakeLists.txt
+++ b/noetic-llama/src/ollamamessages/CMakeLists.txt
@@ -48,11 +48,10 @@ find_package(catkin REQUIRED COMPONENTS
 ##   * add every package in MSG_DEP_SET to generate_messages(DEPENDENCIES ...)
 
 ## Generate messages in the 'msg' folder
-# add_message_files(
-#   FILES
-#   Message1.msg
-#   Message2.msg
-# )
+add_message_files(
+  FILES
+  WhisperTranscription.msg
+)
 
 ## Generate services in the 'srv' folder
 add_service_files(
diff --git a/noetic-llama/src/ollamamessages/msg/WhisperTranscription.msg b/noetic-llama/src/ollamamessages/msg/WhisperTranscription.msg
new file mode 100644
index 0000000..985e998
--- /dev/null
+++ b/noetic-llama/src/ollamamessages/msg/WhisperTranscription.msg
@@ -0,0 +1,6 @@
+string text
+string language
+float64 temperature
+float64 avg_logprob
+float64 compression_ratio
+float64 no_speech_prob
\ No newline at end of file
diff --git a/noetic-llama/src/ollamawrapper/src/ollamawrapper.py b/noetic-llama/src/ollamawrapper/src/ollamawrapper.py
index f344299..0bf0d99 100644
--- a/noetic-llama/src/ollamawrapper/src/ollamawrapper.py
+++ b/noetic-llama/src/ollamawrapper/src/ollamawrapper.py
@@ -87,7 +87,7 @@ def handle_ollama_call(req):
 
 def handle_ollama_server():
     rospy.init_node("ollama_wrapper_server")
-    s = rospy.Service("ollama_wrapper", OllamaCall, handle_ollama_call)
+    s = rospy.Service("/stt/ollamacall", OllamaCall, handle_ollama_call)
     print("Spin")
     rospy.spin()
 
diff --git a/noetic-llama/src/whisperwrapper/CMakeLists.txt b/noetic-llama/src/whisperwrapper/CMakeLists.txt
new file mode 100644
index 0000000..6d3f9a4
--- /dev/null
+++ b/noetic-llama/src/whisperwrapper/CMakeLists.txt
@@ -0,0 +1,206 @@
+cmake_minimum_required(VERSION 3.0.2)
+project(whisperwrapper)
+
+## Compile as C++11, supported in ROS Kinetic and newer
+# add_compile_options(-std=c++11)
+
+## Find catkin macros and libraries
+## if COMPONENTS list like find_package(catkin REQUIRED COMPONENTS xyz)
+## is used, also find other catkin packages
+find_package(catkin REQUIRED COMPONENTS
+  roscpp
+  rospy
+  std_msgs
+)
+
+## System dependencies are found with CMake's conventions
+# find_package(Boost REQUIRED COMPONENTS system)
+
+
+## Uncomment this if the package has a setup.py. This macro ensures
+## modules and global scripts declared therein get installed
+## See http://ros.org/doc/api/catkin/html/user_guide/setup_dot_py.html
+# catkin_python_setup()
+
+################################################
+## Declare ROS messages, services and actions ##
+################################################
+
+## To declare and build messages, services or actions from within this
+## package, follow these steps:
+## * Let MSG_DEP_SET be the set of packages whose message types you use in
+##   your messages/services/actions (e.g. std_msgs, actionlib_msgs, ...).
+## * In the file package.xml:
+##   * add a build_depend tag for "message_generation"
+##   * add a build_depend and a exec_depend tag for each package in MSG_DEP_SET
+##   * If MSG_DEP_SET isn't empty the following dependency has been pulled in
+##     but can be declared for certainty nonetheless:
+##     * add a exec_depend tag for "message_runtime"
+## * In this file (CMakeLists.txt):
+##   * add "message_generation" and every package in MSG_DEP_SET to
+##     find_package(catkin REQUIRED COMPONENTS ...)
+##   * add "message_runtime" and every package in MSG_DEP_SET to
+##     catkin_package(CATKIN_DEPENDS ...)
+##   * uncomment the add_*_files sections below as needed
+##     and list every .msg/.srv/.action file to be processed
+##   * uncomment the generate_messages entry below
+##   * add every package in MSG_DEP_SET to generate_messages(DEPENDENCIES ...)
+
+## Generate messages in the 'msg' folder
+# add_message_files(
+#   FILES
+#   Message1.msg
+#   Message2.msg
+# )
+
+## Generate services in the 'srv' folder
+# add_service_files(
+#   FILES
+#   Service1.srv
+#   Service2.srv
+# )
+
+## Generate actions in the 'action' folder
+# add_action_files(
+#   FILES
+#   Action1.action
+#   Action2.action
+# )
+
+## Generate added messages and services with any dependencies listed here
+# generate_messages(
+#   DEPENDENCIES
+#   std_msgs
+# )
+
+################################################
+## Declare ROS dynamic reconfigure parameters ##
+################################################
+
+## To declare and build dynamic reconfigure parameters within this
+## package, follow these steps:
+## * In the file package.xml:
+##   * add a build_depend and a exec_depend tag for "dynamic_reconfigure"
+## * In this file (CMakeLists.txt):
+##   * add "dynamic_reconfigure" to
+##     find_package(catkin REQUIRED COMPONENTS ...)
+##   * uncomment the "generate_dynamic_reconfigure_options" section below
+##     and list every .cfg file to be processed
+
+## Generate dynamic reconfigure parameters in the 'cfg' folder
+# generate_dynamic_reconfigure_options(
+#   cfg/DynReconf1.cfg
+#   cfg/DynReconf2.cfg
+# )
+
+###################################
+## catkin specific configuration ##
+###################################
+## The catkin_package macro generates cmake config files for your package
+## Declare things to be passed to dependent projects
+## INCLUDE_DIRS: uncomment this if your package contains header files
+## LIBRARIES: libraries you create in this project that dependent projects also need
+## CATKIN_DEPENDS: catkin_packages dependent projects also need
+## DEPENDS: system dependencies of this project that dependent projects also need
+catkin_package(
+#  INCLUDE_DIRS include
+#  LIBRARIES whisperwrapper
+#  CATKIN_DEPENDS roscpp rospy std_msgs
+#  DEPENDS system_lib
+)
+
+###########
+## Build ##
+###########
+
+## Specify additional locations of header files
+## Your package locations should be listed before other locations
+include_directories(
+# include
+  ${catkin_INCLUDE_DIRS}
+)
+
+## Declare a C++ library
+# add_library(${PROJECT_NAME}
+#   src/${PROJECT_NAME}/whisperwrapper.cpp
+# )
+
+## Add cmake target dependencies of the library
+## as an example, code may need to be generated before libraries
+## either from message generation or dynamic reconfigure
+# add_dependencies(${PROJECT_NAME} ${${PROJECT_NAME}_EXPORTED_TARGETS} ${catkin_EXPORTED_TARGETS})
+
+## Declare a C++ executable
+## With catkin_make all packages are built within a single CMake context
+## The recommended prefix ensures that target names across packages don't collide
+# add_executable(${PROJECT_NAME}_node src/whisperwrapper_node.cpp)
+
+## Rename C++ executable without prefix
+## The above recommended prefix causes long target names, the following renames the
+## target back to the shorter version for ease of user use
+## e.g. "rosrun someones_pkg node" instead of "rosrun someones_pkg someones_pkg_node"
+# set_target_properties(${PROJECT_NAME}_node PROPERTIES OUTPUT_NAME node PREFIX "")
+
+## Add cmake target dependencies of the executable
+## same as for the library above
+# add_dependencies(${PROJECT_NAME}_node ${${PROJECT_NAME}_EXPORTED_TARGETS} ${catkin_EXPORTED_TARGETS})
+
+## Specify libraries to link a library or executable target against
+# target_link_libraries(${PROJECT_NAME}_node
+#   ${catkin_LIBRARIES}
+# )
+
+#############
+## Install ##
+#############
+
+# all install targets should use catkin DESTINATION variables
+# See http://ros.org/doc/api/catkin/html/adv_user_guide/variables.html
+
+## Mark executable scripts (Python etc.) for installation
+## in contrast to setup.py, you can choose the destination
+catkin_install_python(PROGRAMS
+  src/whisperwrapper.py
+  DESTINATION ${CATKIN_PACKAGE_BIN_DESTINATION}
+)
+
+## Mark executables for installation
+## See http://docs.ros.org/melodic/api/catkin/html/howto/format1/building_executables.html
+# install(TARGETS ${PROJECT_NAME}_node
+#   RUNTIME DESTINATION ${CATKIN_PACKAGE_BIN_DESTINATION}
+# )
+
+## Mark libraries for installation
+## See http://docs.ros.org/melodic/api/catkin/html/howto/format1/building_libraries.html
+# install(TARGETS ${PROJECT_NAME}
+#   ARCHIVE DESTINATION ${CATKIN_PACKAGE_LIB_DESTINATION}
+#   LIBRARY DESTINATION ${CATKIN_PACKAGE_LIB_DESTINATION}
+#   RUNTIME DESTINATION ${CATKIN_GLOBAL_BIN_DESTINATION}
+# )
+
+## Mark cpp header files for installation
+# install(DIRECTORY include/${PROJECT_NAME}/
+#   DESTINATION ${CATKIN_PACKAGE_INCLUDE_DESTINATION}
+#   FILES_MATCHING PATTERN "*.h"
+#   PATTERN ".svn" EXCLUDE
+# )
+
+## Mark other files for installation (e.g. launch and bag files, etc.)
+# install(FILES
+#   # myfile1
+#   # myfile2
+#   DESTINATION ${CATKIN_PACKAGE_SHARE_DESTINATION}
+# )
+
+#############
+## Testing ##
+#############
+
+## Add gtest based cpp test target and link libraries
+# catkin_add_gtest(${PROJECT_NAME}-test test/test_whisperwrapper.cpp)
+# if(TARGET ${PROJECT_NAME}-test)
+#   target_link_libraries(${PROJECT_NAME}-test ${PROJECT_NAME})
+# endif()
+
+## Add folders to be run by python nosetests
+# catkin_add_nosetests(test)
diff --git a/noetic-llama/src/whisperwrapper/package.xml b/noetic-llama/src/whisperwrapper/package.xml
new file mode 100644
index 0000000..52f3fd7
--- /dev/null
+++ b/noetic-llama/src/whisperwrapper/package.xml
@@ -0,0 +1,68 @@
+<?xml version="1.0"?>
+<package format="2">
+  <name>whisperwrapper</name>
+  <version>0.0.0</version>
+  <description>The whisperwrapper package</description>
+
+  <!-- One maintainer tag required, multiple allowed, one person per tag -->
+  <!-- Example:  -->
+  <!-- <maintainer email="jane.doe@example.com">Jane Doe</maintainer> -->
+  <maintainer email="eden@todo.todo">eden</maintainer>
+
+
+  <!-- One license tag required, multiple allowed, one license per tag -->
+  <!-- Commonly used license strings: -->
+  <!--   BSD, MIT, Boost Software License, GPLv2, GPLv3, LGPLv2.1, LGPLv3 -->
+  <license>TODO</license>
+
+
+  <!-- Url tags are optional, but multiple are allowed, one per tag -->
+  <!-- Optional attribute type can be: website, bugtracker, or repository -->
+  <!-- Example: -->
+  <!-- <url type="website">http://wiki.ros.org/whisperwrapper</url> -->
+
+
+  <!-- Author tags are optional, multiple are allowed, one per tag -->
+  <!-- Authors do not have to be maintainers, but could be -->
+  <!-- Example: -->
+  <!-- <author email="jane.doe@example.com">Jane Doe</author> -->
+
+
+  <!-- The *depend tags are used to specify dependencies -->
+  <!-- Dependencies can be catkin packages or system dependencies -->
+  <!-- Examples: -->
+  <!-- Use depend as a shortcut for packages that are both build and exec dependencies -->
+  <!--   <depend>roscpp</depend> -->
+  <!--   Note that this is equivalent to the following: -->
+  <!--   <build_depend>roscpp</build_depend> -->
+  <!--   <exec_depend>roscpp</exec_depend> -->
+  <!-- Use build_depend for packages you need at compile time: -->
+  <!--   <build_depend>message_generation</build_depend> -->
+  <!-- Use build_export_depend for packages you need in order to build against this package: -->
+  <!--   <build_export_depend>message_generation</build_export_depend> -->
+  <!-- Use buildtool_depend for build tool packages: -->
+  <!--   <buildtool_depend>catkin</buildtool_depend> -->
+  <!-- Use exec_depend for packages you need at runtime: -->
+  <!--   <exec_depend>message_runtime</exec_depend> -->
+  <!-- Use test_depend for packages you need only for testing: -->
+  <!--   <test_depend>gtest</test_depend> -->
+  <!-- Use doc_depend for packages you need only for building documentation: -->
+  <!--   <doc_depend>doxygen</doc_depend> -->
+  <buildtool_depend>catkin</buildtool_depend>
+  <build_depend>roscpp</build_depend>
+  <build_depend>rospy</build_depend>
+  <build_depend>std_msgs</build_depend>
+  <build_export_depend>roscpp</build_export_depend>
+  <build_export_depend>rospy</build_export_depend>
+  <build_export_depend>std_msgs</build_export_depend>
+  <exec_depend>roscpp</exec_depend>
+  <exec_depend>rospy</exec_depend>
+  <exec_depend>std_msgs</exec_depend>
+
+
+  <!-- The export tag contains other, unspecified, tags -->
+  <export>
+    <!-- Other tools can request additional information be placed here -->
+
+  </export>
+</package>
diff --git a/noetic-llama/src/whisperwrapper/src/list_microphones.py b/noetic-llama/src/whisperwrapper/src/list_microphones.py
new file mode 100644
index 0000000..d5b49ff
--- /dev/null
+++ b/noetic-llama/src/whisperwrapper/src/list_microphones.py
@@ -0,0 +1,4 @@
+import speech_recognition as sr
+
+for index, name in enumerate(sr.Microphone.list_microphone_names()):
+    print("Microphone with name \"{1}\" found for `Microphone(device_index={0})`".format(index, name))
\ No newline at end of file
diff --git a/noetic-llama/src/whisperwrapper/src/whisperwrapper.py b/noetic-llama/src/whisperwrapper/src/whisperwrapper.py
new file mode 100644
index 0000000..4ebaebf
--- /dev/null
+++ b/noetic-llama/src/whisperwrapper/src/whisperwrapper.py
@@ -0,0 +1,65 @@
+#!/usr/bin/env python3
+
+from ollamamessages.msg import WhisperTranscription
+
+import speech_recognition as sr
+import tempfile
+import requests
+import rospy 
+import time
+import json
+import os
+
+whisper_api_url = rospy.get_param("/stt/whisper_api_url", "192.168.122.1:9000")
+pause = rospy.get_param("/stt/speech_recogn_pause_time", 0.8)
+energy = rospy.get_param("/stt/speech_recogn_energy", 400) 
+dynamic_energy = rospy.get_param("/stt/speech_recogn_dyn_energy_flag", False)
+microphone_device = rospy.get_param("/stt/microphone_device", 1)
+
+class WhisperWrapper:
+    def __init__(self) -> None:
+        self.transcription_pub = rospy.Publisher("/stt/transcription", WhisperTranscription, queue_size = 1)
+
+        self.record_audio(pause, energy, dynamic_energy, microphone_device)
+
+    def record_audio(self, pause, energy, dynamic_energy, microphone_device):
+        recogniser = sr.Recognizer()
+        recogniser.energy_threshold = energy
+        recogniser.pause_threshold = pause
+        recogniser.dynamic_energy_threshold = dynamic_energy
+
+        with sr.Microphone(sample_rate = 10000) as microphone:
+            rospy.loginfo("Listening...")
+            while True and not rospy.is_shutdown():
+                audio = recogniser.listen(microphone)
+
+                with tempfile.NamedTemporaryFile(mode = "wb", suffix = ".wav", delete = False) as f:
+                    audio_path = f.name
+                    f.write(audio.get_wav_data())
+
+                rospy.loginfo("I heard something... Written to %s" % audio_path)
+                req = requests.post(
+                    "http://%s/asr?output=json" % whisper_api_url,
+                    files = {"audio_file": open(audio_path, "rb")}
+                )
+                os.remove(audio_path)
+                o = req.json()
+                rospy.loginfo("Transcribed '%s'" % o["text"])
+                if o["text"] != "":
+                    self.transcription_pub.publish(
+                        text = o["text"],
+                        language = o["language"],
+                        temperature = o["segments"][0]["temperature"],
+                        avg_logprob = o["segments"][0]["avg_logprob"],
+                        compression_ratio = o["segments"][0]["compression_ratio"],
+                        no_speech_prob = o["segments"][0]["no_speech_prob"]
+                    )
+
+                    
+
+if __name__ == "__main__":
+    rospy.init_node("whisper_wrapper")
+    whisperwrapper = WhisperWrapper()
+    
+
+