Update app.py

app.py

@@ -1,11 +1,9 @@
 import gradio as gr
-import math
-import time
 import numpy as np
-import csv
 from pydub import AudioSegment
 from pydub.silence import detect_nonsilent
 import io
+import csv
 
 
 def numpy_to_audiosegment(audio_array, sampling_rate):
@@ -58,6 +56,30 @@ def format_time(milliseconds):
     return f"{minutes:02}:{secs:02}"
 
 
+def numpy_to_mp3(audio_array, sampling_rate):
+    """Converts a numpy audio array to MP3 format."""
+    # Normalize audio_array if it's floating-point
+    if np.issubdtype(audio_array.dtype, np.floating):
+        max_val = np.max(np.abs(audio_array))
+        audio_array = (audio_array / max_val) * 32767  # Normalize to 16-bit range
+        audio_array = audio_array.astype(np.int16)
+
+    audio_segment = AudioSegment(
+        audio_array.tobytes(),
+        frame_rate=sampling_rate,
+        sample_width=audio_array.dtype.itemsize,
+        channels=1
+    )
+
+    # Export the audio segment to MP3 bytes
+    mp3_io = io.BytesIO()
+    audio_segment.export(mp3_io, format="mp3", bitrate="320k")
+    mp3_bytes = mp3_io.getvalue()
+    mp3_io.close()
+
+    return mp3_bytes
+
+
 def stream(audio, chunk_length_s):
     sampling_rate, array = audio
     audio_segment = numpy_to_audiosegment(array, sampling_rate)
@@ -93,6 +115,7 @@ def stream(audio, chunk_length_s):
         print(f"{start} to {end}")
 
 
+# Gradio Interface
 with gr.Blocks() as demo:
     with gr.Row():
         with gr.Column():