Added voice feedback feature using pyttsx3, which is an offline text-to-speech library.

detect.py

@@ -35,6 +35,7 @@
 import sys
 from pathlib import Path
 
+import pyttsx3
 import torch
 
 FILE = Path(__file__).resolve()
@@ -310,6 +311,15 @@ def write_to_csv(image_name, prediction, confidence):
         # Print time (inference-only)
         LOGGER.info(f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1E3:.1f}ms")
 
+        if s.startswith("0"):
+            engine = pyttsx3.init()
+            engine.say(f"{s.split (':') [1][8:]}")  # Convert label to speech
+            engine.runAndWait()
+        else:
+            engine = pyttsx3.init()
+            engine.say(f"{s.split (':') [2][8:]}")
+            engine.runAndWait()
+
     # Print results
     t = tuple(x.t / seen * 1e3 for x in dt)  # speeds per image
     LOGGER.info(f"Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}" % t)

requirements.txt

@@ -2,6 +2,7 @@
 # Usage: pip install -r requirements.txt
 
 # Base ------------------------------------------------------------------------
+pyttsx3
 gitpython>=3.1.30
 matplotlib>=3.3
 numpy>=1.23.5