Update app.py

app.py

@@ -22,8 +22,13 @@ def get_filename(file_obj):
 
 def audio_to_transcript(file_obj):
     # get all audio segments
-    segments, _ = model_whisper.transcribe(file_obj.name, beam_size=5, vad_filter=True)
-    print("start")
+    try:
+        filename = get_filename(file_obj)
+        segments, _ = model_whisper.transcribe(file_obj.name, beam_size=5, vad_filter=True)
+    except:
+        filename = file_obj.split("/")[-1]
+        segments, _ = model_whisper.transcribe(file_obj, beam_size=5, vad_filter=True)
+ 
     start_segments, end_segments, text_segments = list(), list(), list()
     for segment in segments:
         start, end, text = segment.start, segment.end, segment.text
@@ -37,20 +42,23 @@ def audio_to_transcript(file_obj):
     df["end"] = end_segments
     df["text"] = text_segments
 
-    print(df)
+    csv_file = filename.split(".")[0] + ".csv"
+    df.to_csv(csv_file, encoding="utf-8", index=False)
+    path_to_csv = gr.File.update(value=csv_file, visible=True)
 
-    return get_filename(file_obj), df
+    return filename, path_to_csv, df
 
 ## Gradio interface
 headers = ["start", "end", "text"]
 iface = gr.Interface(fn=audio_to_transcript,
                      inputs=gr.File(label="Audio file"),
                      outputs=[
-                        gr.Textbox(label="Name of the audio file"),
+                        gr.Textbox(label="Audio file name"),
+                        gr.File(label="Transcript csv file"),
                         gr.DataFrame(label="Transcript", headers=headers),
                      ],
                      allow_flagging="never",
                      title="Audio to Transcript",
                      description="Just paste any audio file and get its corresponding transcript with timeline.",
                      )
-iface.launch()
+iface.launch(debug=True)