every_holiday/VRCT
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'optimization' into develop

Browse Source
This commit is contained in:
misygauziya
2023-07-06 13:53:59 +09:00
parent 4f8e6e0014 a5c5090335
commit ac3fc3f29a
8 changed files with 464 additions and 461 deletions
Download Patch File Download Diff File Expand all files Collapse all files

240
VRCT.py
View File

@@ -1,27 +1,29 @@
import os
import json
import queue
from os import path as os_path
from json import load as json_load
from json import dump as json_dump
from queue import Queue
import tkinter as tk
import customtkinter
from PIL import Image
from customtkinter import CTk, CTkFrame, CTkCheckBox, CTkFont, CTkButton, CTkImage, CTkTabview, CTkTextbox, CTkEntry
from PIL.Image import open as Image_open
from flashtext import KeywordProcessor
import utils
import osc_tools
import window_config
import window_information
import languages
import audio_utils
import audio_recorder
import audio_transcriber
import translation
from utils import save_json, print_textbox, thread_fnc
from osc_tools import send_typing, send_message
from window_config import ToplevelWindowConfig
from window_information import ToplevelWindowInformation
from languages import transcription_lang, translators, translation_lang
from audio_utils import get_input_device_list, get_output_device_list, get_default_input_device, get_default_output_device
from audio_recorder import SelectedMicRecorder, SelectedSpeakerRecorder
from audio_transcriber import AudioTranscriber
from translation import Translator
class App(customtkinter.CTk):
class App(CTk):
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
# init instance
self.translator = translation.Translator()
self.translator = Translator()
self.keyword_processor = KeywordProcessor()
# init config
@@ -38,14 +40,14 @@ class App(customtkinter.CTk):
self.UI_SCALING = "100%"
self.FONT_FAMILY = "Yu Gothic UI"
## Translation
self.CHOICE_TRANSLATOR = languages.translators[0]
self.INPUT_SOURCE_LANG = list(languages.translation_lang[self.CHOICE_TRANSLATOR].keys())[0]
self.INPUT_TARGET_LANG = list(languages.translation_lang[self.CHOICE_TRANSLATOR].keys())[1]
self.OUTPUT_SOURCE_LANG = list(languages.translation_lang[self.CHOICE_TRANSLATOR].keys())[1]
self.OUTPUT_TARGET_LANG = list(languages.translation_lang[self.CHOICE_TRANSLATOR].keys())[0]
self.CHOICE_TRANSLATOR = translators[0]
self.INPUT_SOURCE_LANG = list(translation_lang[self.CHOICE_TRANSLATOR].keys())[0]
self.INPUT_TARGET_LANG = list(translation_lang[self.CHOICE_TRANSLATOR].keys())[1]
self.OUTPUT_SOURCE_LANG = list(translation_lang[self.CHOICE_TRANSLATOR].keys())[1]
self.OUTPUT_TARGET_LANG = list(translation_lang[self.CHOICE_TRANSLATOR].keys())[0]
## Transcription Send
self.CHOICE_MIC_DEVICE = audio_utils.get_default_input_device()["name"]
self.INPUT_MIC_VOICE_LANGUAGE = list(languages.transcription_lang.keys())[0]
self.CHOICE_MIC_DEVICE = get_default_input_device()["name"]
self.INPUT_MIC_VOICE_LANGUAGE = list(transcription_lang.keys())[0]
self.INPUT_MIC_ENERGY_THRESHOLD = 300
self.INPUT_MIC_DYNAMIC_ENERGY_THRESHOLD = True
self.INPUT_MIC_RECORD_TIMEOUT = 3
@@ -53,8 +55,8 @@ class App(customtkinter.CTk):
self.INPUT_MIC_MAX_PHRASES = 10
self.INPUT_MIC_WORD_FILTER = []
## Transcription Receive
self.CHOICE_SPEAKER_DEVICE = audio_utils.get_default_output_device()["name"]
self.INPUT_SPEAKER_VOICE_LANGUAGE = list(languages.transcription_lang.keys())[1]
self.CHOICE_SPEAKER_DEVICE = get_default_output_device()["name"]
self.INPUT_SPEAKER_VOICE_LANGUAGE = list(transcription_lang.keys())[1]
self.INPUT_SPEAKER_ENERGY_THRESHOLD = 300
self.INPUT_SPEAKER_DYNAMIC_ENERGY_THRESHOLD = True
self.INPUT_SPEAKER_RECORD_TIMEOUT = 3
@@ -72,9 +74,9 @@ class App(customtkinter.CTk):
self.MESSAGE_FORMAT = "[message]([translation])"
# load config
if os.path.isfile(self.PATH_CONFIG) is not False:
if os_path.isfile(self.PATH_CONFIG) is not False:
with open(self.PATH_CONFIG, 'r') as fp:
config = json.load(fp)
config = json_load(fp)
# main window
if "ENABLE_TRANSLATION" in config.keys():
if type(config["ENABLE_TRANSLATION"]) is bool:
@@ -109,24 +111,24 @@ class App(customtkinter.CTk):
if config["CHOICE_TRANSLATOR"] in list(self.translator.translator_status.keys()):
self.CHOICE_TRANSLATOR = config["CHOICE_TRANSLATOR"]
if "INPUT_SOURCE_LANG" in config.keys():
if config["INPUT_SOURCE_LANG"] in list(languages.translation_lang[self.CHOICE_TRANSLATOR].keys()):
if config["INPUT_SOURCE_LANG"] in list(translation_lang[self.CHOICE_TRANSLATOR].keys()):
self.INPUT_SOURCE_LANG = config["INPUT_SOURCE_LANG"]
if "INPUT_TARGET_LANG" in config.keys():
if config["INPUT_SOURCE_LANG"] in list(languages.translation_lang[self.CHOICE_TRANSLATOR].keys()):
if config["INPUT_SOURCE_LANG"] in list(translation_lang[self.CHOICE_TRANSLATOR].keys()):
self.INPUT_TARGET_LANG = config["INPUT_TARGET_LANG"]
if "OUTPUT_SOURCE_LANG" in config.keys():
if config["INPUT_SOURCE_LANG"] in list(languages.translation_lang[self.CHOICE_TRANSLATOR].keys()):
if config["INPUT_SOURCE_LANG"] in list(translation_lang[self.CHOICE_TRANSLATOR].keys()):
self.OUTPUT_SOURCE_LANG = config["OUTPUT_SOURCE_LANG"]
if "OUTPUT_TARGET_LANG" in config.keys():
if config["INPUT_SOURCE_LANG"] in list(languages.translation_lang[self.CHOICE_TRANSLATOR].keys()):
if config["INPUT_SOURCE_LANG"] in list(translation_lang[self.CHOICE_TRANSLATOR].keys()):
self.OUTPUT_TARGET_LANG = config["OUTPUT_TARGET_LANG"]
# Transcription
if "CHOICE_MIC_DEVICE" in config.keys():
if config["CHOICE_MIC_DEVICE"] in [device["name"] for device in audio_utils.get_input_device_list()]:
if config["CHOICE_MIC_DEVICE"] in [device["name"] for device in get_input_device_list()]:
self.CHOICE_MIC_DEVICE = config["CHOICE_MIC_DEVICE"]
if "INPUT_MIC_VOICE_LANGUAGE" in config.keys():
if config["INPUT_MIC_VOICE_LANGUAGE"] in list(languages.transcription_lang.keys()):
if config["INPUT_MIC_VOICE_LANGUAGE"] in list(transcription_lang.keys()):
self.INPUT_MIC_VOICE_LANGUAGE = config["INPUT_MIC_VOICE_LANGUAGE"]
if "INPUT_MIC_ENERGY_THRESHOLD" in config.keys():
if type(config["INPUT_MIC_ENERGY_THRESHOLD"]) is int:
@@ -148,10 +150,10 @@ class App(customtkinter.CTk):
self.INPUT_MIC_WORD_FILTER = config["INPUT_MIC_WORD_FILTER"]
if "CHOICE_SPEAKER_DEVICE" in config.keys():
if config["CHOICE_SPEAKER_DEVICE"] in [device["name"] for device in audio_utils.get_output_device_list()]:
if config["CHOICE_SPEAKER_DEVICE"] in [device["name"] for device in get_output_device_list()]:
self.CHOICE_SPEAKER_DEVICE = config["CHOICE_SPEAKER_DEVICE"]
if "INPUT_SPEAKER_VOICE_LANGUAGE" in config.keys():
if config["INPUT_SPEAKER_VOICE_LANGUAGE"] in list(languages.transcription_lang.keys()):
if config["INPUT_SPEAKER_VOICE_LANGUAGE"] in list(transcription_lang.keys()):
self.INPUT_SPEAKER_VOICE_LANGUAGE = config["INPUT_SPEAKER_VOICE_LANGUAGE"]
if "INPUT_SPEAKER_ENERGY_THRESHOLD" in config.keys():
if type(config["INPUT_SPEAKER_ENERGY_THRESHOLD"]) is int:
@@ -221,14 +223,14 @@ class App(customtkinter.CTk):
"AUTH_KEYS": self.AUTH_KEYS,
"MESSAGE_FORMAT": self.MESSAGE_FORMAT,
}
json.dump(config, fp, indent=4)
json_dump(config, fp, indent=4)
## set UI theme
customtkinter.set_appearance_mode(self.APPEARANCE_THEME)
customtkinter.set_default_color_theme("blue")
# init main window
self.iconbitmap(os.path.join(os.path.dirname(__file__), "img", "app.ico"))
self.iconbitmap(os_path.join(os_path.dirname(__file__), "img", "app.ico"))
self.title("VRCT")
self.geometry(f"{400}x{175}")
self.minsize(400, 175)
@@ -236,84 +238,84 @@ class App(customtkinter.CTk):
self.grid_rowconfigure(0, weight=1)
# add sidebar left
self.sidebar_frame = customtkinter.CTkFrame(self, corner_radius=0)
self.sidebar_frame = CTkFrame(self, corner_radius=0)
self.sidebar_frame.grid(row=0, column=0, rowspan=4, sticky="nsw")
self.sidebar_frame.grid_rowconfigure(5, weight=1)
# add checkbox translation
self.checkbox_translation = customtkinter.CTkCheckBox(
self.checkbox_translation = CTkCheckBox(
self.sidebar_frame,
text="translation",
onvalue=True,
offvalue=False,
command=self.checkbox_translation_callback,
font=customtkinter.CTkFont(family=self.FONT_FAMILY)
font=CTkFont(family=self.FONT_FAMILY)
)
self.checkbox_translation.grid(row=0, column=0, columnspan=2 ,padx=10, pady=(5, 5), sticky="we")
# add checkbox transcription send
self.checkbox_transcription_send = customtkinter.CTkCheckBox(
self.checkbox_transcription_send = CTkCheckBox(
self.sidebar_frame,
text="voice2chatbox",
onvalue=True,
offvalue=False,
command=self.checkbox_transcription_send_callback,
font=customtkinter.CTkFont(family=self.FONT_FAMILY)
font=CTkFont(family=self.FONT_FAMILY)
)
self.checkbox_transcription_send.grid(row=1, column=0, columnspan=2 ,padx=10, pady=(5, 5), sticky="we")
# add checkbox transcription receive
self.checkbox_transcription_receive = customtkinter.CTkCheckBox(
self.checkbox_transcription_receive = CTkCheckBox(
self.sidebar_frame,
text="speaker2log",
onvalue=True,
offvalue=False,
command=self.checkbox_transcription_receive_callback,
font=customtkinter.CTkFont(family=self.FONT_FAMILY)
font=CTkFont(family=self.FONT_FAMILY)
)
self.checkbox_transcription_receive.grid(row=2, column=0, columnspan=2 ,padx=10, pady=(5, 5), sticky="we")
# add checkbox foreground
self.checkbox_foreground = customtkinter.CTkCheckBox(
self.checkbox_foreground = CTkCheckBox(
self.sidebar_frame,
text="foreground",
onvalue=True,
offvalue=False,
command=self.checkbox_foreground_callback,
font=customtkinter.CTkFont(family=self.FONT_FAMILY)
font=CTkFont(family=self.FONT_FAMILY)
)
self.checkbox_foreground.grid(row=3, column=0, columnspan=2 ,padx=10, pady=(5, 5), sticky="we")
# add button information
self.button_information = customtkinter.CTkButton(
self.button_information = CTkButton(
self.sidebar_frame,
text="",
width=25,
command=self.button_information_callback,
image=customtkinter.CTkImage(Image.open(os.path.join(os.path.dirname(__file__), "img", "info-icon-white.png")))
image=CTkImage(Image_open(os_path.join(os_path.dirname(__file__), "img", "info-icon-white.png")))
)
self.button_information.grid(row=5, column=0, padx=(10, 5), pady=(5, 5), sticky="wse")
self.information_window = None
# add button config
self.button_config = customtkinter.CTkButton(
self.button_config = CTkButton(
self.sidebar_frame,
text="",
width=25,
command=self.button_config_callback,
image=customtkinter.CTkImage(Image.open(os.path.join(os.path.dirname(__file__), "img", "config-icon-white.png")))
image=CTkImage(Image_open(os_path.join(os_path.dirname(__file__), "img", "config-icon-white.png")))
)
self.button_config.grid(row=5, column=1, padx=(5, 10), pady=(5, 5), sticky="wse")
self.config_window = None
# add tabview textbox
self.tabview_logs = customtkinter.CTkTabview(master=self)
self.tabview_logs = CTkTabview(master=self)
self.tabview_logs.add("log")
self.tabview_logs.add("send")
self.tabview_logs.add("receive")
self.tabview_logs.add("system")
self.tabview_logs.grid(row=0, column=1, padx=0, pady=0, sticky="nsew")
self.tabview_logs._segmented_button.configure(font=customtkinter.CTkFont(family=self.FONT_FAMILY))
self.tabview_logs._segmented_button.configure(font=CTkFont(family=self.FONT_FAMILY))
self.tabview_logs._segmented_button.grid(sticky="W")
self.tabview_logs.tab("log").grid_rowconfigure(0, weight=1)
self.tabview_logs.tab("log").grid_columnconfigure(0, weight=1)
@@ -326,42 +328,42 @@ class App(customtkinter.CTk):
self.tabview_logs.configure(fg_color="transparent")
# add textbox message log
self.textbox_message_log = customtkinter.CTkTextbox(
self.textbox_message_log = CTkTextbox(
self.tabview_logs.tab("log"),
font=customtkinter.CTkFont(family=self.FONT_FAMILY)
font=CTkFont(family=self.FONT_FAMILY)
)
self.textbox_message_log.grid(row=0, column=0, padx=0, pady=0, sticky="nsew")
self.textbox_message_log.configure(state='disabled')
# add textbox message send log
self.textbox_message_send_log = customtkinter.CTkTextbox(
self.textbox_message_send_log = CTkTextbox(
self.tabview_logs.tab("send"),
font=customtkinter.CTkFont(family=self.FONT_FAMILY)
font=CTkFont(family=self.FONT_FAMILY)
)
self.textbox_message_send_log.grid(row=0, column=0, padx=0, pady=0, sticky="nsew")
self.textbox_message_send_log.configure(state='disabled')
# add textbox message receive log
self.textbox_message_receive_log = customtkinter.CTkTextbox(
self.textbox_message_receive_log = CTkTextbox(
self.tabview_logs.tab("receive"),
font=customtkinter.CTkFont(family=self.FONT_FAMILY)
font=CTkFont(family=self.FONT_FAMILY)
)
self.textbox_message_receive_log.grid(row=0, column=0, padx=0, pady=0, sticky="nsew")
self.textbox_message_receive_log.configure(state='disabled')
# add textbox message system log
self.textbox_message_system_log = customtkinter.CTkTextbox(
self.textbox_message_system_log = CTkTextbox(
self.tabview_logs.tab("system"),
font=customtkinter.CTkFont(family=self.FONT_FAMILY)
font=CTkFont(family=self.FONT_FAMILY)
)
self.textbox_message_system_log.grid(row=0, column=0, padx=0, pady=0, sticky="nsew")
self.textbox_message_system_log.configure(state='disabled')
# add entry message box
self.entry_message_box = customtkinter.CTkEntry(
self.entry_message_box = CTkEntry(
self,
placeholder_text="message",
font=customtkinter.CTkFont(family=self.FONT_FAMILY)
font=CTkFont(family=self.FONT_FAMILY)
)
self.entry_message_box.grid(row=1, column=1, columnspan=2, padx=5, pady=(5, 10), sticky="nsew")
@@ -369,8 +371,8 @@ class App(customtkinter.CTk):
## set translator
if self.translator.authentication(self.CHOICE_TRANSLATOR, self.AUTH_KEYS[self.CHOICE_TRANSLATOR]) is False:
# error update Auth key
utils.print_textbox(self.textbox_message_log, "Auth Key or language setting is incorrect", "ERROR")
utils.print_textbox(self.textbox_message_system_log, "Auth Key or language setting is incorrect", "ERROR")
print_textbox(self.textbox_message_log, "Auth Key or language setting is incorrect", "ERROR")
print_textbox(self.textbox_message_system_log, "Auth Key or language setting is incorrect", "ERROR")
## set checkbox enable translation
if self.ENABLE_TRANSLATION:
@@ -421,7 +423,7 @@ class App(customtkinter.CTk):
def button_config_callback(self):
if self.config_window is None or not self.config_window.winfo_exists():
self.config_window = window_config.ToplevelWindowConfig(self)
self.config_window = ToplevelWindowConfig(self)
self.checkbox_translation.configure(state="disabled")
self.checkbox_transcription_send.configure(state="disabled")
self.checkbox_transcription_receive.configure(state="disabled")
@@ -429,41 +431,41 @@ class App(customtkinter.CTk):
def button_information_callback(self):
if self.information_window is None or not self.information_window.winfo_exists():
self.information_window = window_information.ToplevelWindowInformation(self)
self.information_window = ToplevelWindowInformation(self)
self.information_window.focus()
def checkbox_translation_callback(self):
self.ENABLE_TRANSLATION = self.checkbox_translation.get()
if self.ENABLE_TRANSLATION:
self.button_config.configure(state="disabled", fg_color=["gray92", "gray14"])
utils.print_textbox(self.textbox_message_log, "Start translation", "INFO")
utils.print_textbox(self.textbox_message_system_log, "Start translation", "INFO")
print_textbox(self.textbox_message_log, "Start translation", "INFO")
print_textbox(self.textbox_message_system_log, "Start translation", "INFO")
else:
if ((self.checkbox_translation.get() is False) and
(self.checkbox_transcription_send.get() is False) and
(self.checkbox_transcription_receive.get() is False)):
self.button_config.configure(state="normal", fg_color=["#3B8ED0", "#1F6AA5"])
utils.print_textbox(self.textbox_message_log, "Stop translation", "INFO")
utils.print_textbox(self.textbox_message_system_log, "Stop translation", "INFO")
utils.save_json(self.PATH_CONFIG, "ENABLE_TRANSLATION", self.ENABLE_TRANSLATION)
print_textbox(self.textbox_message_log, "Stop translation", "INFO")
print_textbox(self.textbox_message_system_log, "Stop translation", "INFO")
save_json(self.PATH_CONFIG, "ENABLE_TRANSLATION", self.ENABLE_TRANSLATION)
def checkbox_transcription_send_callback(self):
self.ENABLE_TRANSCRIPTION_SEND = self.checkbox_transcription_send.get()
if self.ENABLE_TRANSCRIPTION_SEND is True:
self.button_config.configure(state="disabled", fg_color=["gray92", "gray14"])
self.mic_audio_queue = queue.Queue()
mic_device = [device for device in audio_utils.get_input_device_list() if device["name"] == self.CHOICE_MIC_DEVICE][0]
self.mic_audio_recorder = audio_recorder.SelectedMicRecorder(
self.mic_audio_queue = Queue()
mic_device = [device for device in get_input_device_list() if device["name"] == self.CHOICE_MIC_DEVICE][0]
self.mic_audio_recorder = SelectedMicRecorder(
mic_device,
self.INPUT_MIC_ENERGY_THRESHOLD,
self.INPUT_MIC_DYNAMIC_ENERGY_THRESHOLD,
self.INPUT_MIC_RECORD_TIMEOUT,
)
self.mic_audio_recorder.record_into_queue(self.mic_audio_queue)
self.mic_transcriber = audio_transcriber.AudioTranscriber(
self.mic_transcriber = AudioTranscriber(
speaker=False,
source=self.mic_audio_recorder.source,
language=languages.transcription_lang[self.INPUT_MIC_VOICE_LANGUAGE],
language=transcription_lang[self.INPUT_MIC_VOICE_LANGUAGE],
phrase_timeout=self.INPUT_MIC_PHRASE_TIMEOUT,
max_phrases=self.INPUT_MIC_MAX_PHRASES,
)
@@ -473,16 +475,16 @@ class App(customtkinter.CTk):
if len(message) > 0:
# word filter
if len(self.keyword_processor.extract_keywords(message)) != 0:
utils.print_textbox(self.textbox_message_log, f"Detect WordFilter :{message}", "INFO")
utils.print_textbox(self.textbox_message_system_log, f"Detect WordFilter :{message}", "INFO")
print_textbox(self.textbox_message_log, f"Detect WordFilter :{message}", "INFO")
print_textbox(self.textbox_message_system_log, f"Detect WordFilter :{message}", "INFO")
return
# translate
if self.checkbox_translation.get() is False:
voice_message = f"{message}"
elif self.translator.translator_status[self.CHOICE_TRANSLATOR] is False:
utils.print_textbox(self.textbox_message_log, "Auth Key or language setting is incorrect", "ERROR")
utils.print_textbox(self.textbox_message_system_log, "Auth Key or language setting is incorrect", "ERROR")
print_textbox(self.textbox_message_log, "Auth Key or language setting is incorrect", "ERROR")
print_textbox(self.textbox_message_system_log, "Auth Key or language setting is incorrect", "ERROR")
voice_message = f"{message}"
else:
result = self.translator.translate(
@@ -495,49 +497,49 @@ class App(customtkinter.CTk):
if self.checkbox_transcription_send.get() is True:
# send OSC message
osc_tools.send_message(voice_message, self.OSC_IP_ADDRESS, self.OSC_PORT)
send_message(voice_message, self.OSC_IP_ADDRESS, self.OSC_PORT)
# update textbox message log
utils.print_textbox(self.textbox_message_log, f"{voice_message}", "SEND")
utils.print_textbox(self.textbox_message_send_log, f"{voice_message}", "SEND")
print_textbox(self.textbox_message_log, f"{voice_message}", "SEND")
print_textbox(self.textbox_message_send_log, f"{voice_message}", "SEND")
self.mic_print_transcript = utils.thread_fnc(mic_transcript_to_chatbox)
self.mic_print_transcript = thread_fnc(mic_transcript_to_chatbox)
self.mic_print_transcript.daemon = True
self.mic_print_transcript.start()
utils.print_textbox(self.textbox_message_log, "Start voice2chatbox", "INFO")
utils.print_textbox(self.textbox_message_system_log, "Start voice2chatbox", "INFO")
print_textbox(self.textbox_message_log, "Start voice2chatbox", "INFO")
print_textbox(self.textbox_message_system_log, "Start voice2chatbox", "INFO")
else:
if ((self.checkbox_translation.get() is False) and
(self.checkbox_transcription_send.get() is False) and
(self.checkbox_transcription_receive.get() is False)):
self.button_config.configure(state="normal", fg_color=["#3B8ED0", "#1F6AA5"])
if isinstance(self.mic_print_transcript, utils.thread_fnc):
if isinstance(self.mic_print_transcript, thread_fnc):
self.mic_print_transcript.stop()
if self.mic_audio_recorder.stop != None:
self.mic_audio_recorder.stop()
self.mic_audio_recorder.stop = None
utils.print_textbox(self.textbox_message_log, "Stop voice2chatbox", "INFO")
utils.print_textbox(self.textbox_message_system_log, "Stop voice2chatbox", "INFO")
utils.save_json(self.PATH_CONFIG, "ENABLE_TRANSCRIPTION_SEND", self.ENABLE_TRANSCRIPTION_SEND)
print_textbox(self.textbox_message_log, "Stop voice2chatbox", "INFO")
print_textbox(self.textbox_message_system_log, "Stop voice2chatbox", "INFO")
save_json(self.PATH_CONFIG, "ENABLE_TRANSCRIPTION_SEND", self.ENABLE_TRANSCRIPTION_SEND)
def checkbox_transcription_receive_callback(self):
self.ENABLE_TRANSCRIPTION_RECEIVE = self.checkbox_transcription_receive.get()
if self.ENABLE_TRANSCRIPTION_RECEIVE is True:
self.button_config.configure(state="disabled", fg_color=["gray92", "gray14"])
self.spk_audio_queue = queue.Queue()
spk_device = [device for device in audio_utils.get_output_device_list() if device["name"] == self.CHOICE_SPEAKER_DEVICE][0]
self.spk_audio_recorder = audio_recorder.SelectedSpeakerRecorder(
self.spk_audio_queue = Queue()
spk_device = [device for device in get_output_device_list() if device["name"] == self.CHOICE_SPEAKER_DEVICE][0]
self.spk_audio_recorder = SelectedSpeakerRecorder(
spk_device,
self.INPUT_SPEAKER_ENERGY_THRESHOLD,
self.INPUT_SPEAKER_DYNAMIC_ENERGY_THRESHOLD,
self.INPUT_SPEAKER_RECORD_TIMEOUT,
)
self.spk_audio_recorder.record_into_queue(self.spk_audio_queue)
self.spk_transcriber = audio_transcriber.AudioTranscriber(
self.spk_transcriber = AudioTranscriber(
speaker=True,
source=self.spk_audio_recorder.source,
language=languages.transcription_lang[self.INPUT_SPEAKER_VOICE_LANGUAGE],
language=transcription_lang[self.INPUT_SPEAKER_VOICE_LANGUAGE],
phrase_timeout=self.INPUT_SPEAKER_PHRASE_TIMEOUT,
max_phrases=self.INPUT_SPEAKER_MAX_PHRASES,
)
@@ -550,8 +552,8 @@ class App(customtkinter.CTk):
if self.checkbox_translation.get() is False:
voice_message = f"{message}"
elif self.translator.translator_status[self.CHOICE_TRANSLATOR] is False:
utils.print_textbox(self.textbox_message_log, "Auth Key or language setting is incorrect", "ERROR")
utils.print_textbox(self.textbox_message_system_log, "Auth Key or language setting is incorrect", "ERROR")
print_textbox(self.textbox_message_log, "Auth Key or language setting is incorrect", "ERROR")
print_textbox(self.textbox_message_system_log, "Auth Key or language setting is incorrect", "ERROR")
voice_message = f"{message}"
else:
result = self.translator.translate(
@@ -562,47 +564,47 @@ class App(customtkinter.CTk):
)
voice_message = self.MESSAGE_FORMAT.replace("[message]", message).replace("[translation]", result)
# send OSC message
# osc_tools.send_message(voice_message, self.OSC_IP_ADDRESS, self.OSC_PORT)
# send_message(voice_message, self.OSC_IP_ADDRESS, self.OSC_PORT)
if self.checkbox_transcription_receive.get() is True:
# update textbox message receive log
utils.print_textbox(self.textbox_message_log, f"{voice_message}", "RECEIVE")
utils.print_textbox(self.textbox_message_receive_log, f"{voice_message}", "RECEIVE")
print_textbox(self.textbox_message_log, f"{voice_message}", "RECEIVE")
print_textbox(self.textbox_message_receive_log, f"{voice_message}", "RECEIVE")
self.spk_print_transcript = utils.thread_fnc(spk_transcript_to_textbox)
self.spk_print_transcript = thread_fnc(spk_transcript_to_textbox)
self.spk_print_transcript.daemon = True
self.spk_print_transcript.start()
utils.print_textbox(self.textbox_message_log, "Start speaker2log", "INFO")
utils.print_textbox(self.textbox_message_system_log, "Start speaker2log", "INFO")
print_textbox(self.textbox_message_log, "Start speaker2log", "INFO")
print_textbox(self.textbox_message_system_log, "Start speaker2log", "INFO")
else:
if ((self.checkbox_translation.get() is False) and
(self.checkbox_transcription_send.get() is False) and
(self.checkbox_transcription_receive.get() is False)):
self.button_config.configure(state="normal", fg_color=["#3B8ED0", "#1F6AA5"])
if isinstance(self.spk_print_transcript, utils.thread_fnc):
if isinstance(self.spk_print_transcript, thread_fnc):
self.spk_print_transcript.stop()
if self.spk_audio_recorder.stop != None:
self.spk_audio_recorder.stop()
self.spk_audio_recorder.stop = None
utils.print_textbox(self.textbox_message_log, "Stop speaker2log", "INFO")
utils.print_textbox(self.textbox_message_system_log, "Stop speaker2log", "INFO")
utils.save_json(self.PATH_CONFIG, "ENABLE_TRANSCRIPTION_RECEIVE", self.ENABLE_TRANSCRIPTION_RECEIVE)
print_textbox(self.textbox_message_log, "Stop speaker2log", "INFO")
print_textbox(self.textbox_message_system_log, "Stop speaker2log", "INFO")
save_json(self.PATH_CONFIG, "ENABLE_TRANSCRIPTION_RECEIVE", self.ENABLE_TRANSCRIPTION_RECEIVE)
def checkbox_foreground_callback(self):
self.ENABLE_FOREGROUND = self.checkbox_foreground.get()
if self.ENABLE_FOREGROUND:
self.attributes("-topmost", True)
utils.print_textbox(self.textbox_message_log, "Start foreground", "INFO")
utils.print_textbox(self.textbox_message_system_log, "Start foreground", "INFO")
print_textbox(self.textbox_message_log, "Start foreground", "INFO")
print_textbox(self.textbox_message_system_log, "Start foreground", "INFO")
else:
self.attributes("-topmost", False)
utils.print_textbox(self.textbox_message_log, "Stop foreground", "INFO")
utils.print_textbox(self.textbox_message_system_log, "Stop foreground", "INFO")
utils.save_json(self.PATH_CONFIG, "ENABLE_FOREGROUND", self.ENABLE_FOREGROUND)
print_textbox(self.textbox_message_log, "Stop foreground", "INFO")
print_textbox(self.textbox_message_system_log, "Stop foreground", "INFO")
save_json(self.PATH_CONFIG, "ENABLE_FOREGROUND", self.ENABLE_FOREGROUND)
def entry_message_box_press_key_enter(self, event):
# send OSC typing
osc_tools.send_typing(False, self.OSC_IP_ADDRESS, self.OSC_PORT)
send_typing(False, self.OSC_IP_ADDRESS, self.OSC_PORT)
if self.ENABLE_FOREGROUND:
self.attributes("-topmost", True)
@@ -613,8 +615,8 @@ class App(customtkinter.CTk):
if self.checkbox_translation.get() is False:
chat_message = f"{message}"
elif self.translator.translator_status[self.CHOICE_TRANSLATOR] is False:
utils.print_textbox(self.textbox_message_log, "Auth Key or language setting is incorrect", "ERROR")
utils.print_textbox(self.textbox_message_system_log, "Auth Key or language setting is incorrect", "ERROR")
print_textbox(self.textbox_message_log, "Auth Key or language setting is incorrect", "ERROR")
print_textbox(self.textbox_message_system_log, "Auth Key or language setting is incorrect", "ERROR")
chat_message = f"{message}"
else:
result = self.translator.translate(
@@ -626,24 +628,24 @@ class App(customtkinter.CTk):
chat_message = self.MESSAGE_FORMAT.replace("[message]", message).replace("[translation]", result)
# send OSC message
osc_tools.send_message(chat_message, self.OSC_IP_ADDRESS, self.OSC_PORT)
send_message(chat_message, self.OSC_IP_ADDRESS, self.OSC_PORT)
# update textbox message log
utils.print_textbox(self.textbox_message_log, f"{chat_message}", "SEND")
utils.print_textbox(self.textbox_message_send_log, f"{chat_message}", "SEND")
print_textbox(self.textbox_message_log, f"{chat_message}", "SEND")
print_textbox(self.textbox_message_send_log, f"{chat_message}", "SEND")
# delete message in entry message box
# self.entry_message_box.delete(0, customtkinter.END)
def entry_message_box_press_key_any(self, event):
# send OSC typing
osc_tools.send_typing(True, self.OSC_IP_ADDRESS, self.OSC_PORT)
send_typing(True, self.OSC_IP_ADDRESS, self.OSC_PORT)
if self.ENABLE_FOREGROUND:
self.attributes("-topmost", False)
def entry_message_box_leave(self, event):
# send OSC typing
osc_tools.send_typing(False, self.OSC_IP_ADDRESS, self.OSC_PORT)
send_typing(False, self.OSC_IP_ADDRESS, self.OSC_PORT)
if self.ENABLE_FOREGROUND:
self.attributes("-topmost", True)

14
audio_recorder.py
View File

@@ -1,10 +1,10 @@
import speech_recognition as sr
import pyaudiowpatch as pyaudio
from speech_recognition import Recognizer, Microphone
from pyaudiowpatch import get_sample_size, paInt16
from datetime import datetime
class BaseRecorder:
def __init__(self, source, energy_threshold, dynamic_energy_threshold, record_timeout):
self.recorder = sr.Recognizer()
self.recorder = Recognizer()
self.recorder.energy_threshold = energy_threshold
self.recorder.dynamic_energy_threshold = dynamic_energy_threshold
self.record_timeout = record_timeout
@@ -20,14 +20,14 @@ class BaseRecorder:
self.recorder.adjust_for_ambient_noise(self.source)
def record_into_queue(self, audio_queue):
def record_callback(_, audio:sr.AudioData) -> None:
def record_callback(_, audio):
audio_queue.put((audio.get_raw_data(), datetime.now()))
self.stop = self.recorder.listen_in_background(self.source, record_callback, phrase_time_limit=self.record_timeout)
class SelectedMicRecorder(BaseRecorder):
def __init__(self, device, energy_threshold, dynamic_energy_threshold, record_timeout):
source=sr.Microphone(
source=Microphone(
device_index=device['index'],
sample_rate=int(device["defaultSampleRate"]),
)
@@ -37,10 +37,10 @@ class SelectedMicRecorder(BaseRecorder):
class SelectedSpeakerRecorder(BaseRecorder):
def __init__(self, device, energy_threshold, dynamic_energy_threshold, record_timeout):
source = sr.Microphone(speaker=True,
source = Microphone(speaker=True,
device_index= device["index"],
sample_rate=int(device["defaultSampleRate"]),
chunk_size=pyaudio.get_sample_size(pyaudio.paInt16),
chunk_size=get_sample_size(paInt16),
channels=device["maxInputChannels"]
)
super().__init__(source=source, energy_threshold=energy_threshold, dynamic_energy_threshold=dynamic_energy_threshold, record_timeout=record_timeout)

21
audio_transcriber.py
View File

@@ -1,9 +1,9 @@
import io
import threading
from io import BytesIO
from threading import Event
import wave
import speech_recognition as sr
from speech_recognition import Recognizer, AudioData, AudioFile
from datetime import timedelta
import pyaudiowpatch as pyaudio
from pyaudiowpatch import get_sample_size, paInt16
PHRASE_TIMEOUT = 3
MAX_PHRASES = 10
@@ -15,8 +15,8 @@ class AudioTranscriber:
self.phrase_timeout = phrase_timeout
self.max_phrases = max_phrases
self.transcript_data = []
self.transcript_changed_event = threading.Event()
self.audio_recognizer = sr.Recognizer()
self.transcript_changed_event = Event()
self.audio_recognizer = Recognizer()
self.audio_sources = {
"sample_rate": source.SAMPLE_RATE,
"sample_width": source.SAMPLE_WIDTH,
@@ -59,19 +59,18 @@ class AudioTranscriber:
source_info["last_spoken"] = time_spoken
def process_mic_data(self):
audio_data = sr.AudioData(self.audio_sources["last_sample"], self.audio_sources["sample_rate"], self.audio_sources["sample_width"])
audio_data = AudioData(self.audio_sources["last_sample"], self.audio_sources["sample_rate"], self.audio_sources["sample_width"])
return audio_data
def process_speaker_data(self):
temp_file = io.BytesIO()
temp_file = BytesIO()
with wave.open(temp_file, 'wb') as wf:
wf.setnchannels(self.audio_sources["channels"])
p = pyaudio.PyAudio()
wf.setsampwidth(p.get_sample_size(pyaudio.paInt16))
wf.setsampwidth(get_sample_size(paInt16))
wf.setframerate(self.audio_sources["sample_rate"])
wf.writeframes(self.audio_sources["last_sample"])
temp_file.seek(0)
with sr.AudioFile(temp_file) as source:
with AudioFile(temp_file) as source:
audio = self.audio_recognizer.record(source)
return audio

18
audio_utils.py
View File

@@ -1,9 +1,9 @@
import pyaudiowpatch as pyaudio
from pyaudiowpatch import PyAudio, paWASAPI
def get_input_device_list():
devices = []
with pyaudio.PyAudio() as p:
wasapi_info = p.get_host_api_info_by_type(pyaudio.paWASAPI)
with PyAudio() as p:
wasapi_info = p.get_host_api_info_by_type(paWASAPI)
for host_index in range(0, p.get_host_api_count()):
for device_index in range(0, p. get_host_api_info_by_index(host_index)['deviceCount']):
device = p.get_device_info_by_host_api_device_index(host_index, device_index)
@@ -13,16 +13,16 @@ def get_input_device_list():
def get_output_device_list():
devices =[]
with pyaudio.PyAudio() as p:
wasapi_info = p.get_host_api_info_by_type(pyaudio.paWASAPI)
with PyAudio() as p:
wasapi_info = p.get_host_api_info_by_type(paWASAPI)
for device in p.get_loopback_device_info_generator():
if device["hostApi"] == wasapi_info["index"] and device["isLoopbackDevice"] is True:
devices.append(device)
return devices
def get_default_input_device():
with pyaudio.PyAudio() as p:
wasapi_info = p.get_host_api_info_by_type(pyaudio.paWASAPI)
with PyAudio() as p:
wasapi_info = p.get_host_api_info_by_type(paWASAPI)
defaultInputDevice = wasapi_info["defaultInputDevice"]
for host_index in range(0, p.get_host_api_count()):
@@ -33,8 +33,8 @@ def get_default_input_device():
return default_device
def get_default_output_device():
with pyaudio.PyAudio() as p:
wasapi_info = p.get_host_api_info_by_type(pyaudio.paWASAPI)
with PyAudio() as p:
wasapi_info = p.get_host_api_info_by_type(paWASAPI)
defaultOutputDevice = wasapi_info["defaultOutputDevice"]
for host_index in range(0, p.get_host_api_count()):

22
translation.py
View File

@@ -1,13 +1,13 @@
import deepl
import deepl_translate
import translators as ts
import languages
from deepl import Translator as deepl_Translator
from deepl_translate import translate as deepl_web_Translator
from translators import translate_text as other_web_Translator
from languages import translators, translation_lang
# Translator
class Translator():
def __init__(self):
self.translator_status = {}
for translator in languages.translators:
for translator in translators:
self.translator_status[translator] = False
self.deepl_client = None
@@ -18,7 +18,7 @@ class Translator():
self.translator_status["DeepL(web)"] = True
result = True
elif translator_name == "DeepL(auth)":
self.deepl_client = deepl.Translator(authkey)
self.deepl_client = deepl_Translator(authkey)
self.deepl_client.translate_text(" ", target_lang="EN-US")
self.translator_status["DeepL(auth)"] = True
result = True
@@ -35,10 +35,10 @@ class Translator():
def translate(self, translator_name, source_language, target_language, message):
result = ""
try:
source_language=languages.translation_lang[translator_name][source_language]
target_language=languages.translation_lang[translator_name][target_language]
source_language=translation_lang[translator_name][source_language]
target_language=translation_lang[translator_name][target_language]
if translator_name == "DeepL(web)":
result = deepl_translate.translate(
result = deepl_web_Translator(
source_language=source_language,
target_language=target_language,
text=message
@@ -50,14 +50,14 @@ class Translator():
target_lang=target_language,
).text
elif translator_name == "Google(web)":
result = ts.translate_text(
result = other_web_Translator(
query_text=message,
translator="google",
from_language=source_language,
to_language=target_language,
)
elif translator_name == "Bing(web)":
result = ts.translate_text(
result = other_web_Translator(
query_text=message,
translator="bing",
from_language=source_language,

16
utils.py
View File

@@ -1,16 +1,16 @@
import json
import datetime
import threading
from json import load, dump
from datetime import datetime
from threading import Thread, Event
def save_json(path, key, value):
with open(path, "r") as fp:
json_data = json.load(fp)
json_data = load(fp)
json_data[key] = value
with open(path, "w") as fp:
json.dump(json_data, fp, indent=4)
dump(json_data, fp, indent=4)
def print_textbox(textbox, message, tags=None):
now = datetime.datetime.now()
now = datetime.now()
now = now.strftime('%H:%M:%S')
textbox.tag_config("ERROR", foreground="#FF0000")
@@ -25,11 +25,11 @@ def print_textbox(textbox, message, tags=None):
textbox.configure(state='disabled')
textbox.see("end")
class thread_fnc(threading.Thread):
class thread_fnc(Thread):
def __init__(self, fnc, daemon=True, *args, **kwargs):
super(thread_fnc, self).__init__(daemon=daemon, *args, **kwargs)
self.fnc = fnc
self._stop = threading.Event()
self._stop = Event()
def stop(self):
self._stop.set()
def stopped(self):

586
window_config.py
View File

File diff suppressed because it is too large Load Diff

8
window_information.py
View File

@@ -1,7 +1,7 @@
import os
import customtkinter
from customtkinter import CTkToplevel, CTkTextbox, CTkFont
class ToplevelWindowInformation(customtkinter.CTkToplevel):
class ToplevelWindowInformation(CTkToplevel):
def __init__(self, parent, *args, **kwargs):
super().__init__(parent, *args, **kwargs)
self.parent = parent
@@ -13,9 +13,9 @@ class ToplevelWindowInformation(customtkinter.CTkToplevel):
self.after(200, lambda: self.iconbitmap(os.path.join(os.path.dirname(__file__), "img", "app.ico")))
self.title("Information")
# create textbox information
self.textbox_information = customtkinter.CTkTextbox(
self.textbox_information = CTkTextbox(
self,
font=customtkinter.CTkFont(family=self.parent.FONT_FAMILY)
font=CTkFont(family=self.parent.FONT_FAMILY)
)
self.textbox_information.grid(row=0, column=0, padx=(10, 10), pady=(10, 10), sticky="nsew")
textbox_information_message = """VRCT(v1.2)