Fixing waiting event

convert_mkv_wav.py

@@ -0,0 +1,7 @@
+import subprocess
+
+def convert(mkv_file):
+    command = "ffmpeg -i {0} -ab 160k -ac 2 -ar 44100 -vn audio.wav".format(mkv_file)
+
+    subprocess.call(command, shell=True)
+

speech-to-text.py

@@ -0,0 +1,50 @@
+#!/usr/bin/env python3
+
+import speech_recognition as sr
+# obtain path to "english.wav" in the same folder as this script
+from os import path
+from convert_mkv_wav import convert
+from pyChatGPT import ChatGPT
+import logging
+# ChatGTP Session token
+logging.basicConfig(level=logging.DEBUG)
+session_tocken = '<YOUR SESSION TOKEN>'
+
+# convert to wav format
+convert('audio.mkv')
+
+AUDIO_FILE = path.join(path.dirname(path.realpath(__file__)), "audio.wav")
+
+# use the audio file as the audio source
+r = sr.Recognizer()
+with sr.AudioFile(AUDIO_FILE) as source:
+    audio = r.record(source)  # read the entire audio file
+
+# Using a microphone
+# with sr.Microphone() as source:
+#   #Chama a funcao de reducao de ruido disponivel na speech_recognition
+#   r.adjust_for_ambient_noise(source)
+#   #Avisa ao usuario que esta pronto para ouvir
+#   print("Speak: ")
+#   #Armazena a informacao de audio na variavel
+#   audio = r.listen(source)
+
+# recognize speech using Google Speech Recognition
+try:
+    # for testing purposes, we're just using the default API key
+    # to use another API key, use `r.recognize_google(audio, key="GOOGLE_SPEECH_RECOGNITION_API_KEY")`
+    # instead of `r.recognize_google(audio)`
+    msg  = r.recognize_google(audio, language='pt-BR')
+    print("Transcript> " + msg)    
+    # Here you can set your conversation id - OR just remove it
+    api = ChatGPT(session_token, conversation_id='9f02d513-c6de-4cfa-898b-cd6fba91dbd9')
+    enhanced_text = api.send_message('Corrija esse trecho: '+msg)
+    print("ChatGPT> " + enhanced_text['message'])
+    output = open('enhanced-text.txt', 'w')
+    output.write(enhanced_text['message'])
+    output.close()
+except sr.UnknownValueError:
+    print("Google Speech Recognition could not understand audio")
+except sr.RequestError as e:
+    print("Could not request results from Google Speech Recognition service; {0}".format(e))
+

src/pyChatGPT/pyChatGPT.py

@@ -15,12 +15,12 @@
 import re
 import os
 
-
 cf_challenge_form = (By.ID, 'challenge-form')
-
 chatgpt_textbox = (By.TAG_NAME, 'textarea')
 chatgpt_streaming = (By.CLASS_NAME, 'result-streaming')
 chatgpt_big_response = (By.XPATH, '//div[@class="flex-1 overflow-hidden"]//div[p]')
+# NOTE: The event result-streaming does not exists anymore. Thus, now Im waiting for the loading button event
+chatgpt_streaming = (By.CLASS_NAME, 'text-2xl')
 chatgpt_small_response = (
     By.XPATH,
     '//div[starts-with(@class, "markdown prose w-full break-words")]',
@@ -408,7 +408,7 @@ def send_message(self, message: str, stream: bool = False) -> dict:
         self.__ensure_cf()
 
         self.logger.debug('Sending message...')
-        textbox = WebDriverWait(self.driver, 5).until(
+        textbox = WebDriverWait(self.driver, 8).until(
             EC.element_to_be_clickable(chatgpt_textbox)
         )
         textbox.click()
@@ -422,16 +422,18 @@ def send_message(self, message: str, stream: bool = False) -> dict:
             message,
         )
         textbox.send_keys(Keys.ENTER)
-
+        textbox.send_keys(Keys.ENTER)
+        # check the result-streaming tag (it doesnt seems to work) 
         if stream:
             for i in self.__stream_message():
                 print(i, end='')
                 time.sleep(0.1)
             return print()
-
+        time.sleep(1)
         self.logger.debug('Waiting for completion...')
-        WebDriverWait(self.driver, 120).until_not(
-            EC.presence_of_element_located(chatgpt_streaming)
+        # FIXED: new chatgpt_streaming
+        WebDriverWait(self.driver, 200).until_not(
+            EC.presence_of_element_located(chatgpt_streaming)            
         )
 
         self.logger.debug('Getting response...')
@@ -509,3 +511,4 @@ def refresh_chat_page(self) -> None:
         self.driver.get(chatgpt_chat_url)
         self.__check_capacity(chatgpt_chat_url)
         self.__check_blocking_elements()
+