converting audio to wav pcm, accept name with spaces

app.py

@@ -15,21 +15,26 @@ matplotlib.use('Agg')
 logging.basicConfig(level=logging.INFO)
 logging.getLogger()
 
+def convert_to_wav(filename):
+
+    os.rename(filename, filename.replace(" ", "_"))
+
+    filename = filename.replace(" ", "_")
+
+    new_name = f"{os.path.splitext(filename)[0]}_converted.wav".replace(" ", "_")
+
+    command = f"ffmpeg -i {filename} -f wav -bitexact -acodec pcm_s16le -ar 22050 -ac 1 {new_name} -y"
+      
+    subprocess.run(command.split())
+
+    return new_name
+
 def get_chunk_times(in_filename, silence_threshold, silence_duration=1):
 
         silence_duration_re = re.compile('silence_duration: (\d+.\d+)')
         silence_end_re = re.compile('silence_end: (\d+.\d+)\s')
 
-        logging.info(f"File {in_filename} exists? = {os.path.exists(in_filename)}")        
-
-        fpath = Path(in_filename).absolute()
-        
-        logging.info(f"Absolue path: {fpath}")
-
         command = f"ffmpeg -i {in_filename} -af silencedetect=n=-{silence_threshold}dB:d={silence_duration} -f null - "
-        #out = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
-
-        #stdout, stderr = out.communicate()
        
         out = subprocess.run(command.split(), stdout=subprocess.PIPE, stderr=subprocess.STDOUT, text=True)
         stdout = out.stdout
@@ -62,7 +67,7 @@ def get_audio_plot(filename, chunks):
 
     duration = len(audioBuffer)/sampleRate
 
-    time = np.arange(0,duration,1/sampleRate) #time vector
+    time = np.arange(0,duration,1/sampleRate)
 
     ax.plot(time,audioBuffer)
     y1 = min(audioBuffer)
@@ -74,20 +79,20 @@ def get_audio_plot(filename, chunks):
 
     plt.xlabel('Time [s]')
     plt.ylabel('Amplitude')
-    plt.title(os.path.basename(filename))
+    plt.title("Audio with silence marks")
 
     return plt.gcf()
     
 
 def get_audio_info(audio):
-    audio = "Rocha_teste.wav"
-    ts, chunks = get_chunk_times(audio, 30, 1)
-    p = get_audio_plot(audio, chunks)
+    new_audio = convert_to_wav(audio)
+    ts, chunks = get_chunk_times(new_audio, 30, 1)
+    p = get_audio_plot(new_audio, chunks)
     return str(ts), p
 
-otext = gr.outputs.Textbox(type="auto", label="Silence time")
+otext = gr.outputs.Textbox(type="auto", label="Silence time:")
 
-oplot = gr.outputs.Image(type="plot", label=None)
+oplot = gr.outputs.Image(type="plot", label="Audio with silence in gray areas")
 
 iaudio = gr.inputs.Audio(source="upload", type="filepath", label=None)
 
@@ -95,7 +100,7 @@ iface = gr.Interface(
     get_audio_info,
     iaudio,
     [otext, oplot],
-    description="Enter .WAV audio to view silence areas",
+    description="Enter audio to view silence areas",
 )
 
 iface.launch()