Update app.py

app.py

@@ -12,6 +12,22 @@ from huggingface_hub import hf_hub_download, InferenceClient
 import requests
 from bs4 import BeautifulSoup
 import urllib
+import random
+
+# List of user agents to choose from for requests
+_useragent_list = [
+    'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:66.0) Gecko/20100101 Firefox/66.0',
+    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36',
+    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36',
+    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36',
+    'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36',
+    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36 Edg/111.0.1661.62',
+    'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/111.0'
+]
+
+def get_useragent():
+    """Returns a random user agent from the list."""
+    return random.choice(_useragent_list)
 
 def extract_text_from_webpage(html_content):
     """Extracts visible text from HTML content using BeautifulSoup."""
@@ -36,7 +52,7 @@ def search(term, num_results=3, lang="en", advanced=True, timeout=5, safe="activ
         while start < num_results:
             resp = session.get(
                 url="https://www.google.com/search",
-                headers={"User-Agent":'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36 Edg/111.0.1661.62'},
+                headers={"User-Agent":get_useragent()},
                 params={
                     "q": term,
                     "num": num_results - start,
@@ -126,13 +142,7 @@ def model(text, web_search):
         return "".join([response.token.text for response in stream if response.token.text != "</s>"])
 
 async def respond(audio, web_search):
-    audio_data, sr = audio  # Unpack the audio tuple
-    with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as tmp_file:
-        tmp_path = tmp_file.name
-        audio_segment = AudioSegment(data=audio_data, sample_width=2, frame_rate=sr, channels=1)  # Assuming 16-bit PCM audio
-        audio_segment.export(tmp_path, format="wav")
-
-    user = transcribe(tmp_path)
+    user = transcribe(audio)
     reply = model(user, web_search)
     communicate = edge_tts.Communicate(reply)
     with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as tmp_file: