Update app.py

app.py

@@ -12,6 +12,8 @@ import torchaudio
 from pydub import AudioSegment
 import io
 import librosa
+import ffmpeg
+
 #from torchaudio.io import CodecConfig
 # import numpy
 
@@ -113,38 +115,24 @@ def main():
             # Define CodecConfig for MP3 compression
             #codec_config = CodecConfig(format="mp3", compression=128)  # 128 kbps for MP3
             #wav3, sample_rate = librosa.load("test.mp3")
-            wav3, sample_rate = torchaudio.load("test.mp3")
-            st.markdown(wav3)
+
+            # Convert input MP3 to WAV
+            ffmpeg.input("test.mp3").output("test.wav").run()
+            wav3, sample_rate = torchaudio.load("test.wav")
+            wav= wav3.unsqueeze(0)
+            file_extension =".wav"
             #RuntimeError: Could not infer dtype of numpy.float32
             #wav = torch.tensor(wav3).float() / 32768.0
             
             #RuntimeError: Numpy is not available
-            wav = torch.from_numpy(wav3) #/32768.0
-            wav = wav.unsqueeze(0).unsqueeze(0)
+            # wav = torch.from_numpy(wav3) #/32768.0
+            # wav = wav.unsqueeze(0).unsqueeze(0)
             st.markdown("Before unsqueeze mp3")
             st.markdown(wav)
         
         #Unsqueeze for line 176
         # wav= wav.unsqueeze(0)
 
-        # #2nd way
-        # # Convert the tensor to a byte-like object in WAV format
-        # with io.BytesIO() as buffer:
-        # # Save the audio to the buffer using torchaudio
-        #     torchaudio.save(buffer, wav, default_sr, format="wav")
-        # # Get the byte data from the buffer
-        #     wav = buffer.getvalue()
-        # # Play the audio file (WAV format)
-        # st.audio(wav, format="audio/wav")
-        
-        # wav, sample_rate = torchaudio.load(audio_file, format="mp3/wav")
-        # st.markdown("SR")
-        # st.markdown(sample_rate)
-        # st.markdown("after unsqueeze wav or mp3")
-        # st.markdown(wav)
-        # 展示文件到页面上
-        # st.audio(tmp_input_audio_file, format="audio/wav")
-
         action = st.selectbox("Select Action", ["Add Watermark", "Decode Watermark"])
 
         if action == "Add Watermark":