Update app.py

app.py

@@ -6,20 +6,18 @@ import os
 import numpy as np
 import base64
 
-genres = ["Pop", "Rock", "Jazz", "Electronic", "Hip-Hop", "Classical", 
- "Lofi", "Chillpop","Country","R&G", "Folk","Heavy Metal", 
+genres = ["Pop", "Rock", "Jazz", "Electronic", "Hip-Hop", "Classical",
+ "Lofi", "Chillpop","Country","R&G", "Folk","Heavy Metal",
  "EDM", "Soil", "Funk","Reggae", "Disco", "Punk Rock", "House",
- "Techno","Indie Rock", "Grunge", "Ambient","Gospel", ]
+ "Techno","Indie Rock", "Grunge", "Ambient","Gospel" ]
 
 @st.cache_resource()
 def load_model():
  model = MusicGen.get_pretrained('facebook/musicgen-medium')
  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,
@@ -27,9 +25,9 @@ def generate_music_tensors(descriptions, duration: int):
  duration=duration
  )
 
- with st.spinner("Generating Music with Medium-Model..."):
+ with st.spinner("Generating Music..."):
  output = model.generate(
- descriptions=descriptions,
+ descriptions=description,
  progress=True,
  return_tokens=True
  )
@@ -37,10 +35,9 @@ def generate_music_tensors(descriptions, duration: int):
  st.success("Music Generation Complete!")
  return output
 
-
-def save_audio(samples: torch.Tensor):
+def save_audio(samples: torch.Tensor, filename):
  sample_rate = 30000
- save_path = "audio_output" 
+ save_path = "/content/drive/MyDrive/Colab Notebooks/audio_output"
  assert samples.dim() == 2 or samples.dim() == 3
 
  samples = samples.detach().cpu()
@@ -48,8 +45,9 @@ def save_audio(samples: torch.Tensor):
  samples = samples[None, ...]
 
  for idx, audio in enumerate(samples):
- audio_path = os.path.join(save_path, f"audio_{idx}.wav")
+ audio_path = os.path.join(save_path, f"{filename}_{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:
@@ -64,56 +62,37 @@ st.set_page_config(
 )
 
 def main():
- with st.sidebar:
- st.header("""⚙🎶 Craft Musical Creations 🎶""",divider="rainbow")
- st.text("")
- st.subheader("1. Enter your music description.......")
- bpm = st.number_input("Enter Speed in BPM", min_value=60)
-
- text_area = st.text_area('Ex : 80s rock song with guitar and drums')
- st.text('')
- # Dropdown for genres
- selected_genre = st.selectbox("Select Genre", genres)
- 
- st.subheader("2. Select time duration (In Seconds)")
- time_slider = st.slider("Select time duration (In Seconds)", 0, 60, 10)
- # time_slider = st.slider("Select time duration (In Minutes)", 0,300,10, step=1)
-
-
- st.title("""🎵 AI Composer Medium-Model 🎵""")
- st.text('')
- left_co,right_co = st.columns(2)
- left_co.write("""Music Generation with Prompts""")
- left_co.write(("""First generation may take some time ......."""))
- 
- if st.sidebar.button('Lets Generate !'):
- with left_co:
- st.text('')
- st.text('')
- st.text('')
- st.text('')
- st.text('')
- st.text('')
- st.text('\n\n')
- st.subheader("Generated Music")
-
- # Generate audio
- # descriptions = [f"{text_area} {selected_genre} {bpm} BPM" for _ in range(5)]
- descriptions = [f"{text_area} {selected_genre} {bpm} BPM" for _ in range(1)] # Change the batch size to 1
- music_tensors = generate_music_tensors(descriptions, time_slider)
-
- # 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'audio_output/audio_{idx}.wav'
- audio_file = open(audio_filepath, 'rb')
- audio_bytes = audio_file.read()
-
- # 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)
+ st.title("🎧AI Composer Medium-Model 🎧")
+
+ st.subheader("Generate Music")
+ st.write("Craft your perfect melody! Fill in the blanks below to create your music masterpiece:")
+
+ bpm = st.number_input("Enter Speed in BPM", min_value=60)
+ text_area = st.text_area('Example: 80s rock song with guitar and drums')
+ selected_genre = st.selectbox("Select Genre", genres)
+ time_slider = st.slider("Select time duration (In Seconds)", 0, 30, 10)
+
+ st.write("Additional options")
+ mood = st.selectbox("Select Mood", ["Happy", "Sad", "Angry", "Relaxed", "Energetic"])
+ instrument = st.selectbox("Select Instrument", ["Piano", "Guitar", "Flute", "Violin", "Drums"])
+ tempo = st.selectbox("Select Tempo", ["Slow", "Moderate", "Fast"])
+ melody = st.text_input("Enter Melody or Chord Progression", "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")
+
+ description = f"{text_area} {selected_genre} {bpm} BPM {mood} {instrument} {tempo} {melody}"
+ music_tensors = generate_music_tensors(description, time_slider)
+
+ idx = 0
+ audio_path = save_audio(music_tensors[idx], "audio_output")
+ audio_file = open(audio_path, 'rb')
+ audio_bytes = audio_file.read()
+
+ st.audio(audio_bytes, format='audio/wav')
+ st.markdown(get_binary_file_downloader_html(audio_path, f'Audio_{idx}'), unsafe_allow_html=True)
 
 if __name__ == "__main__":
  main()
+