Update app.py

app.py

@@ -439,6 +439,33 @@ pipe_asr = pipeline("automatic-speech-recognition", model=model, tokenizer=proce
 
 base_audio_drive = "/data/audio"
 
+#Normal Code with sample rate is 44100 Hz
+
+# def transcribe_function(stream, new_chunk):
+#     try:
+#         sr, y = new_chunk[0], new_chunk[1]
+#     except TypeError:
+#         print(f"Error chunk structure: {type(new_chunk)}, content: {new_chunk}")
+#         return stream, "", None
+
+#     y = y.astype(np.float32) / np.max(np.abs(y))
+
+#     if stream is not None:
+#         stream = np.concatenate([stream, y])
+#     else:
+#         stream = y
+
+#     result = pipe_asr({"array": stream, "sampling_rate": sr}, return_timestamps=False)
+
+#     full_text = result.get("text","")
+    
+#     return stream, full_text, result
+
+# Resampling code with 16000 Hz
+
+import numpy as np
+from scipy.signal import resample
+
 def transcribe_function(stream, new_chunk):
     try:
         sr, y = new_chunk[0], new_chunk[1]
@@ -446,6 +473,13 @@ def transcribe_function(stream, new_chunk):
         print(f"Error chunk structure: {type(new_chunk)}, content: {new_chunk}")
         return stream, "", None
 
+    # Resample to 16000 Hz
+    target_sr = 16000
+    if sr != target_sr:
+        num_samples = int(len(y) * float(target_sr) / sr)
+        y = resample(y, num_samples)
+        sr = target_sr
+
     y = y.astype(np.float32) / np.max(np.abs(y))
 
     if stream is not None:
@@ -455,7 +489,7 @@ def transcribe_function(stream, new_chunk):
 
     result = pipe_asr({"array": stream, "sampling_rate": sr}, return_timestamps=False)
 
-    full_text = result.get("text","")
+    full_text = result.get("text", "")
     
     return stream, full_text, result