Update app.py

app.py

@@ -176,7 +176,7 @@ def create_interface():
         ```
         
         ### Audio Requirements
-        - Format: WAV files
+        - Format: .wav files
         - Sample rate: Any (automatically resampled to 16kHz)
         - Channels: Mono or stereo (converted to mono)
         - Number of files: Equal number of references and outputs
@@ -184,9 +184,9 @@ def create_interface():
         ## Output Format
         
         The tool generates a ZIP file containing:
-        - `ps_scores_{model}.csv`: PS scores for each speaker/source
-        - `pm_scores_{model}.csv`: PM scores for each speaker/source
-        - `params.json`: Experiment parameters used
+        - `ps_scores_{model}.csv`: PS scores for each source
+        - `pm_scores_{model}.csv`: PM scores for each source
+        - `params.json`: Parameters used
         - `manifest_canonical.json`: File mapping and processing details
         
         ## Available Models
@@ -194,14 +194,14 @@ def create_interface():
         | Model | Description | Default Layer | Use Case |
         |-------|-------------|---------------|----------|
         | `raw` | Raw waveform features | N/A | Baseline comparison |
-        | `wavlm` | WavLM Large | 24 | Best overall performance |
-        | `wav2vec2` | Wav2Vec2 Large | 24 | Strong performance |
-        | `hubert` | HuBERT Large | 24 | Good for speech |
-        | `wavlm_base` | WavLM Base | 12 | Faster, good quality |
-        | `wav2vec2_base` | Wav2Vec2 Base | 12 | Faster processing |
-        | `hubert_base` | HuBERT Base | 12 | Faster for speech |
+        | `wavlm` | WavLM Large | 24 | Strong performance |
+        | `wav2vec2` | Wav2Vec2 Large | 24 | Best overall performance |
+        | `hubert` | HuBERT Large | 24 | |
+        | `wavlm_base` | WavLM Base | 12 |  |
+        | `wav2vec2_base` | Wav2Vec2 Base | 12 | Faster, good quality |
+        | `hubert_base` | HuBERT Base | 12 | |
         | `wav2vec2_xlsr` | Wav2Vec2 XLSR-53 | 24 | Multilingual |
-        | `ast` | Audio Spectrogram Transformer | 12 | General audio |
+        | `ast` | Audio Spectrogram Transformer | 12 | Music |
         
         ## Parameters
         
@@ -213,7 +213,7 @@ def create_interface():
         
         ## Citation
         
-        If you use MAPSS in your research, please cite:
+        If you use MAPSS, please cite:
         
         ```bibtex
         @article{Ivry2025MAPSS,
@@ -317,27 +317,8 @@ def create_interface():
                     max_lines=10
                 )
         
-        gr.Markdown("""
-        ## Output format:
-        The results ZIP will contain:
-        - `ps_scores_{model}.csv`: Perceptual Similarity scores for each speaker/source
-        - `pm_scores_{model}.csv`: Perceptual Matching scores for each speaker/source  
-        - `params.json`: Experiment parameters
-        - `manifest_canonical.json`: Processed file manifest
-        
-        ## Score interpretation:
-        - **PS (Perceptual Similarity)**: 0-1 score, higher is better. Measures how well the separated output matches the reference compared to other sources.
-        - **PM (Perceptual Matching)**: 0-1 score, higher is better. Measures robustness to audio distortions.
-        
-        ## Notes:
-        - Processing may take several minutes depending on the audio length and model
-        - Audio files are automatically resampled to 16kHz
-        - The tool automatically matches outputs to references based on correlation
-        - For best results, ensure equal number of reference and output files
-        
-        ## Citation:
-        If you use this tool in your research, please cite our paper (details coming soon).
-        """)
+        # gr.Markdown("""
+        # """)
         
         # Set up the processing
         process_btn.click(