Update app.py

app.py

@@ -20,10 +20,8 @@ def load_model():
     model = MusicGen.get_pretrained('facebook/musicgen-small')
     return model
 
-def generate_music_tensors(descriptions, duration: int):
+def generate_music_tensors(description, duration: int):
     model = load_model()
-    # model = load_model().to('cpu')
-
 
     model.set_generation_params(
         use_sampling=True,
@@ -33,7 +31,7 @@ def generate_music_tensors(descriptions, duration: int):
 
     with st.spinner("Generating Music..."):
         output = model.generate(
-            descriptions=descriptions,
+            descriptions=description,
             progress=True,
             return_tokens=True
         )
@@ -54,6 +52,7 @@ def save_audio(samples: torch.Tensor):
     for idx, audio in enumerate(samples):
         audio_path = os.path.join(save_path, f"audio_{idx}.wav")
         torchaudio.save(audio_path, audio, sample_rate)
+        return audio_path
 
 def get_binary_file_downloader_html(bin_file, file_label='File'):
     with open(bin_file, 'rb') as f:
@@ -80,52 +79,29 @@ def main():
 
     st.subheader("2. Select time duration (In Seconds)")
     time_slider = st.slider("Select time duration (In Seconds)", 0, 30, 10)
-    # mood = st.selectbox("Select Mood (Optional)", ["Happy", "Sad", "Angry", "Relaxed", "Energetic"], None)
-    # instrument = st.selectbox("Select Instrument (Optional)", ["Piano", "Guitar", "Flute", "Violin", "Drums"], None)
-    # tempo = st.selectbox("Select Tempo (Optional)", ["Slow", "Moderate", "Fast"], None)
-    # melody = st.text_input("Enter Melody or Chord Progression (Optional)", "e.g: C D:min G:7 C, Twinkle Twinkle Little Star")
 
     if st.button('Let\'s Generate 🎶'):
         st.text('\n\n')
         st.subheader("Generated Music")
-        descriptions = [f"{text_area} {selected_genre} {bpm} BPM" for _ in range(1)]  # Change the batch size to 1
-        
-        # Generate audio
-        # description = text_area  # Initialize description with text_area
-        # if selected_genre:
-        #     description += f" {selected_genre}"
-        #     st.empty()  # Hide the selected_genre selectbox after selecting one option
-        # if bpm:
-        #     description += f" {bpm} BPM"
-        # if mood:
-        #     description += f" {mood}"
-        #     st.empty()  # Hide the mood selectbox after selecting one option
-        # if instrument:
-        #     description += f" {instrument}"
-        #     st.empty()  # Hide the instrument selectbox after selecting one option
-        # if tempo:
-        #     description += f" {tempo}"
-        #     st.empty()  # Hide the tempo selectbox after selecting one option
-        # if melody:
-        #     description += f" {melody}" 
 
+        description = f"{text_area} {selected_genre} {bpm} BPM"
+        
         # Clear CUDA memory cache before generating music
         torch.cuda.empty_cache()
 
         music_tensors = generate_music_tensors(description, time_slider)
 
- # Only play the full audio for index 0
+        # Only play the full audio for index 0
         idx = 0
         music_tensor = music_tensors[idx]
-        save_music_file = save_audio(music_tensor)
-        audio_filepath = f'output/audio_{idx}.wav'
+        audio_filepath = save_audio(music_tensor)
         audio_file = open(audio_filepath, 'rb')
         audio_bytes = audio_file.read()
 
-            # Play the full audio
+        # Play the full audio
         st.audio(audio_bytes, format='audio/wav')
         st.markdown(get_binary_file_downloader_html(audio_filepath, f'Audio_{idx}'), unsafe_allow_html=True)
 
 
 if __name__ == "__main__":
-    main()
+    main()