feat(app): remove config in spaces

app.py

@@ -38,20 +38,17 @@ def create_vc_fn(tgt_sr, net_g, vc, if_f0, file_index):
                 asyncio.run(edge_tts.Communicate(tts_text, "-".join(tts_voice.split('-')[:-1])).save("tts.mp3"))
                 audio, sr = librosa.load("tts.mp3", sr=16000, mono=True)
             else:
-                if config.files:
-                    audio, sr = librosa.load(input_audio, sr=16000, mono=True)
-                else:
-                    if input_audio is None:
-                        return "You need to upload an audio", None
-                    sampling_rate, audio = input_audio
-                    duration = audio.shape[0] / sampling_rate
-                    if duration > 20 and limitation:
-                        return "Please upload an audio file that is less than 20 seconds. If you need to generate a longer audio file, please use Colab.", None
-                    audio = (audio / np.iinfo(audio.dtype).max).astype(np.float32)
-                    if len(audio.shape) > 1:
-                        audio = librosa.to_mono(audio.transpose(1, 0))
-                    if sampling_rate != 16000:
-                        audio = librosa.resample(audio, orig_sr=sampling_rate, target_sr=16000)
+                if input_audio is None:
+                    return "You need to upload an audio", None
+                sampling_rate, audio = input_audio
+                duration = audio.shape[0] / sampling_rate
+                if duration > 20 and limitation:
+                    return "Please upload an audio file that is less than 20 seconds. If you need to generate a longer audio file, please use Colab.", None
+                audio = (audio / np.iinfo(audio.dtype).max).astype(np.float32)
+                if len(audio.shape) > 1:
+                    audio = librosa.to_mono(audio.transpose(1, 0))
+                if sampling_rate != 16000:
+                    audio = librosa.resample(audio, orig_sr=sampling_rate, target_sr=16000)
             times = [0, 0, 0]
             f0_up_key = int(f0_up_key)
             audio_opt = vc.pipeline(