Speech-Listener 0.1__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (14) hide show
  1. speech_listener-0.1/MANIFEST.in +5 -0
  2. speech_listener-0.1/PKG-INFO +8 -0
  3. speech_listener-0.1/Speech_Listener/Web_folder/index.html +15 -0
  4. speech_listener-0.1/Speech_Listener/Web_folder/script.js +34 -0
  5. speech_listener-0.1/Speech_Listener/Web_folder/style.css +10 -0
  6. speech_listener-0.1/Speech_Listener/__init__.py +2 -0
  7. speech_listener-0.1/Speech_Listener/main.py +54 -0
  8. speech_listener-0.1/Speech_Listener.egg-info/PKG-INFO +8 -0
  9. speech_listener-0.1/Speech_Listener.egg-info/SOURCES.txt +12 -0
  10. speech_listener-0.1/Speech_Listener.egg-info/dependency_links.txt +1 -0
  11. speech_listener-0.1/Speech_Listener.egg-info/requires.txt +2 -0
  12. speech_listener-0.1/Speech_Listener.egg-info/top_level.txt +1 -0
  13. speech_listener-0.1/setup.cfg +4 -0
  14. speech_listener-0.1/setup.py +14 -0
speech_listener-0.1/MANIFEST.in ADDED
@@ -0,0 +1,5 @@
1
+ # MANIFEST.in
2
+
3
+ include speech_listener/web/index.html
4
+ include speech_listener/web/script.js
5
+ include speech_listener/web/style.css
speech_listener-0.1/PKG-INFO ADDED
@@ -0,0 +1,8 @@
1
+ Metadata-Version: 2.4
2
+ Name: Speech_Listener
3
+ Version: 0.1
4
+ Summary: A speech recognition listener using Selenium and Web Speech API
5
+ Requires-Dist: selenium
6
+ Requires-Dist: webdriver_manager
7
+ Dynamic: requires-dist
8
+ Dynamic: summary
speech_listener-0.1/Speech_Listener/Web_folder/index.html ADDED
@@ -0,0 +1,15 @@
1
+ <!DOCTYPE html>
2
+ <html lang="eng">
3
+ <head>
4
+ <meta charset="UTF-8">
5
+ <meta name="viewport" content="width=divice-width, initial-sclae=1.0" >
6
+ <title>SpeechToText</title>
7
+ <link rel="stylesheet" href="style.css">
8
+ </head>
9
+ <body>
10
+ <h1>SpeechToText</h1>
11
+ <button id="startButton">Start listening</button>
12
+ <div id="output"></div>
13
+ <script src="script.js"></script>
14
+ </body>
15
+ </html>
speech_listener-0.1/Speech_Listener/Web_folder/script.js ADDED
@@ -0,0 +1,34 @@
1
+ const output = document.getElementById("output");
2
+ const startButton = document.getElementById("startButton");
3
+ let finalTranscript = "";
4
+
5
+ const SpeechRecognition = window.SpeechRecognition || window.webkitSpeechRecognition
6
+
7
+ const recognition = new SpeechRecognition();
8
+ recognition.lang = "en-US";
9
+ recognition.interimResults = true;
10
+ startButton.addEventListener("click", () => {
11
+ finalTranscript = '';
12
+ output.textContent = '';
13
+ recognition.start();
14
+ startButton.textContent = "Listening";
15
+ });
16
+
17
+ recognition.addEventListener("result", (e) => {
18
+ const transcript = Array.from(e.results).map(result => result[0].transcript).join("");
19
+ if(e.results[0].isFinal){
20
+ finalTranscript = transcript;
21
+ output.textContent = finalTranscript;
22
+ }
23
+ });
24
+
25
+ recognition.addEventListener("end", () => {
26
+ startButton.textContent = 'Start Listening';
27
+ recognition.start();
28
+ });
29
+ document.addEventListener('keydown', (e) => {
30
+ if(e.key == 'Escape'){
31
+ recognition.stop();
32
+ startButton.textContent = 'Start Listening';
33
+ }
34
+ })
speech_listener-0.1/Speech_Listener/Web_folder/style.css ADDED
@@ -0,0 +1,10 @@
1
+ body{
2
+ font-family: 'Lucida Sans', 'Lucida Sans Regular', 'Lucida Grande', 'Lucida Sans Unicode', Geneva, Verdana, sans-serif;
3
+ text-align: center;
4
+ }
5
+ #output{
6
+ margin-top: 20px;
7
+ padding: 10px;
8
+ border: 1px solid;
9
+ min-height: 100px;
10
+ }
speech_listener-0.1/Speech_Listener/__init__.py ADDED
@@ -0,0 +1,2 @@
1
+ # Here, . in (.main) means look in the same package folder (i.e. Speech_Listener)
2
+ from .main import listen # exposes listen function globally
speech_listener-0.1/Speech_Listener/main.py ADDED
@@ -0,0 +1,54 @@
1
+ from selenium import webdriver
2
+ from selenium.webdriver.common.by import By
3
+ from selenium.webdriver.support.ui import WebDriverWait
4
+ from selenium.webdriver.support import expected_conditions as EC
5
+ from selenium.webdriver.chrome.service import Service
6
+ from webdriver_manager.chrome import ChromeDriverManager
7
+ import os
8
+
9
+ # from selenium.webdriver.chrome.options import Options
10
+
11
+ BASE_dir = os.path.dirname(os.path.abspath(__file__))
12
+
13
+ chrome_options = webdriver.ChromeOptions()
14
+ # driver = webdriver.Chrome(service=Service(ChromeDriverManager().install()), options = chrome_options)
15
+ # driver.get("https://www.youtube.com")
16
+
17
+ # it allows auto access of Microphone to Chrome
18
+ chrome_options.add_argument("--use-fake-ui-for-media-stream")
19
+ chrome_options.add_argument("--headless=new")
20
+
21
+ driver = webdriver.Chrome(service=Service(ChromeDriverManager().install()), options = chrome_options)
22
+
23
+ website = os.path.join(BASE_dir, "web", "index.html")
24
+ driver.get(f"file:///{website}")
25
+
26
+ rec_file = os.path.join(BASE_dir, "input.txt")
27
+
28
+ def listen():
29
+ try:
30
+ start_button = WebDriverWait(driver, 20).until(EC.element_to_be_clickable((By.ID, "startButton")))
31
+ start_button.click()
32
+ print('Listening ...')
33
+ output_text = ""
34
+ is_second_click = False
35
+ while True:
36
+ output_element = WebDriverWait(driver, 20).until(EC.presence_of_element_located((By.ID, "output")))
37
+ current_text = output_element.text.strip()
38
+
39
+ if "Start Listening" in start_button.text and current_text != output_text:
40
+ output_text = current_text
41
+ try:
42
+ with open(rec_file, "w") as file:
43
+ file.write(current_text.lower())
44
+ # print('\r', end='', flush=True)
45
+ print(f"Divyanshu : {current_text}")
46
+ except Exception as e:
47
+ print(f'File write error : {e}')
48
+
49
+ except KeyboardInterrupt:
50
+ print('Stopping ....') # Pressed Ctrl + C
51
+ except Exception as e:
52
+ print(f"Error : {e}")
53
+
54
+ listen()
speech_listener-0.1/Speech_Listener.egg-info/PKG-INFO ADDED
@@ -0,0 +1,8 @@
1
+ Metadata-Version: 2.4
2
+ Name: Speech_Listener
3
+ Version: 0.1
4
+ Summary: A speech recognition listener using Selenium and Web Speech API
5
+ Requires-Dist: selenium
6
+ Requires-Dist: webdriver_manager
7
+ Dynamic: requires-dist
8
+ Dynamic: summary
speech_listener-0.1/Speech_Listener.egg-info/SOURCES.txt ADDED
@@ -0,0 +1,12 @@
1
+ MANIFEST.in
2
+ setup.py
3
+ Speech_Listener/__init__.py
4
+ Speech_Listener/main.py
5
+ Speech_Listener.egg-info/PKG-INFO
6
+ Speech_Listener.egg-info/SOURCES.txt
7
+ Speech_Listener.egg-info/dependency_links.txt
8
+ Speech_Listener.egg-info/requires.txt
9
+ Speech_Listener.egg-info/top_level.txt
10
+ Speech_Listener/Web_folder/index.html
11
+ Speech_Listener/Web_folder/script.js
12
+ Speech_Listener/Web_folder/style.css
speech_listener-0.1/Speech_Listener.egg-info/requires.txt ADDED
@@ -0,0 +1,2 @@
1
+ selenium
2
+ webdriver_manager
speech_listener-0.1/Speech_Listener.egg-info/top_level.txt ADDED
@@ -0,0 +1 @@
1
+ Speech_Listener
speech_listener-0.1/setup.cfg ADDED
@@ -0,0 +1,4 @@
1
+ [egg_info]
2
+ tag_build =
3
+ tag_date = 0
4
+
speech_listener-0.1/setup.py ADDED
@@ -0,0 +1,14 @@
1
+ from setuptools import setup, find_packages
2
+
3
+ setup(
4
+ name="Speech_Listener", # name of the Package
5
+ version="0.1",
6
+ description="A speech recognition listener using Selenium and Web Speech API",
7
+ packages = find_packages(),
8
+ package_data={"Speech_Listener" : ["Web_folder/*"]}, # include all files from Web_folder
9
+ include_package_data=True, # works together with MANIFEST.in
10
+ install_requires=[ # your dependencies (auto-installs for users)
11
+ "selenium",
12
+ "webdriver_manager"
13
+ ]
14
+ )