Update app.py

app.py

@@ -33,7 +33,7 @@ def initialize_model(config, ckpt):
 
     return sampler
 
-sampler = initialize_model('configs/text_to_audio/txt2audio_args.yaml', 'useful_ckpts/maa1_caps.ckpt')
+sampler = initialize_model('configs/text_to_audio/txt2audio_args.yaml', 'useful_ckpts/maa1_full.ckpt')
 vocoder = VocoderBigVGAN('vocoder/logs/bigvnat',device=device)
 clap_model = CLAPWrapper('useful_ckpts/CLAP/CLAP_weights_2022.pth','useful_ckpts/CLAP/config.yml',use_cuda=torch.cuda.is_available())
 
@@ -114,7 +114,7 @@ with gr.Blocks() as demo:
                 ddim_steps = gr.Slider(label="Steps", minimum=1,
                                        maximum=150, value=100, step=1)
                 scale = gr.Slider(
-                    label="Guidance Scale:(Large => more relevant to text but the quality may drop)", minimum=0.1, maximum=4.0, value=1.5, step=0.1
+                    label="Guidance Scale:(Large => more relevant to text but the quality may drop)", minimum=0.1, maximum=8.0, value=3.0, step=0.1
                 )
                 seed = gr.Slider(
                     label="Seed:Change this value (any integer number) will lead to a different generation result.",
@@ -136,8 +136,8 @@ with gr.Blocks() as demo:
     with gr.Row():
         with gr.Column():
             gr.Examples(
-                        examples = [['a dog barking and a bird chirping',100,3,2,55],['fireworks pop and explode',100,3,2,55],
-                                        ['piano and violin plays',100,3,2,55],['wind thunder and rain falling',100,3,2,55],['music made by drum kit',100,3,2,55]],
+                        examples = [['a dog barking and a bird chirping',100,3,3,55],['Pigeons peck, coo, and flap their wings before a man speaks',100,3,3,55],
+                                        ['music of violin and piano',100,3,2,88],['wind thunder and rain falling',100,3,3,55],['music made by drum kit',100,3,3,55]],
                         inputs = [prompt,ddim_steps, num_samples, scale, seed],
                         outputs = [outaudio]
                         )