Update app.py

app.py

@@ -175,12 +175,16 @@ with gr.Blocks(theme=theme, css=css) as demo:
             ## 🎶YourMT3+: Multi-instrument Music Transcription with Enhanced Transformer Architectures and Cross-dataset Stem Augmentation
             ## Model card:
             - Model name: `{model_name}`
+            <details>
+            <summary>Details</summary>
+
             - Encoder backbone: Perceiver-TF + Mixture of Experts (2/8)
             - Decoder backbone: Multi-channel T5-small
             - Tokenizer: MT3 tokens with Singing extension
             - Dataset: YourMT3 dataset
             - Augmentation strategy: Intra-/Cross dataset stem augment, No Pitch-shifting
             - FP Precision: BF16-mixed for training, FP16 for inference
+            </details>
             
             ## Caution:
             - Currently running on CPU, and it takes longer than 3 minutes for a 30-second input. Please try [GPU-HuggingFace-demo](mimbres/YourMT3) for fast inference.