ver1

.gitattributes

@@ -1,35 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,6 +1,6 @@
 ---
-title: AIA-Scope
-emoji: 🔍
+title: Speech-Scope
+emoji: 🎤
 colorFrom: gray
 colorTo: indigo
 sdk: gradio
@@ -10,10 +10,18 @@ pinned: false
 license: ecl-2.0
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+## Speech-Scope
+
+Análise de métricas de áudio.
+
+Confira a referência de configuração em [Hugging Face Spaces Config Reference](https://huggingface.co/docs/hub/spaces-config-reference).
+
+## Desenvolvedor
 
 Desenvolvido por Ramon Mayor Martins (2023)
-mail rmayormartins@gmail.com 
-hp https://rmayormartins.github.io/
-twitter @rmayormartins 
-github https://github.com/rmayormartins
+
+- E-mail: [rmayormartins@gmail.com](mailto:rmayormartins@gmail.com)
+- Homepage: [https://rmayormartins.github.io/](https://rmayormartins.github.io/)
+- Twitter: [@rmayormartins](https://twitter.com/rmayormartins)
+- GitHub: [https://github.com/rmayormartins](https://github.com/rmayormartins)
+

app.py

@@ -1,304 +1,83 @@
 import gradio as gr
-from zipfile import ZipFile, BadZipFile
+import librosa
+import numpy as np
+import matplotlib.pyplot as plt
 import tempfile
-import os
-import re
-import pandas as pd
-import collections
-import json
-import glob
-from io import BytesIO
+import librosa.display
 
 
-ai_patterns = [
-    "PIC*", "PersonalImageClassifier*", "Look*", "LookExtension*", "ChatBot", "ImageBot", "TMIC","TeachableMachine*",
-    "TeachableMachineImageClassifier*", "SpeechRecognizer*", "FaceExtension*","Pose*","Posenet","PosenetExtension", "Eliza*", "Alexa*"
-]
-
-
-drawing_and_animation_patterns = ["Ball", "Canvas", "ImageSprite"]
-maps_patterns = ["Map", "Marker", "Circle", "FeatureCollection", "LineString", "Navigation","Polygon", "Retangle" ]
-sensors_patterns = ["AccelerometerSensor", "BarcodeScanner", "Barometer", "Clock", "GyroscopeSensor", "Hygrometer", "LightSensor", "LocationSensor", "MagneticFieldSensor", "NearField","OrientationSensor", "ProximitySensor","Thermometer", "Pedometer"]
-social_patterns = ["ContactPicker", "EmailPicker", "PhoneCall", "PhoneNumberPicker", "Texting", "Twitter"]
-storage_patterns = ["File", "CloudDB", "DataFile", "Spreadsheet", "FusiontablesControl", "TinyDB", "TinyWebDB"]
-connectivity_patterns = ["BluetoothClient", "ActivityStarter", "Serial", "BluetoothServer", "Web"]
-
-
-def extract_components_using_regex(scm_content):
-    pattern = r'"\$Type":"(.*?)"'
-    components = re.findall(pattern, scm_content)
-    if 'roboflow' in scm_content.lower():
-        components.append("Using Roboflow")
-    return components
-
-
-def extract_category_components(components, patterns):
-    category_components = []
-    for component in components:
-        for pattern in patterns:
-            if component.startswith(pattern):
-                category_components.append(component)
-    return category_components
-
-
-def extract_extensions_from_aia(file_path: str):
-    extensions = []
-    with ZipFile(file_path, 'r') as zip_ref:
-        for file_path in zip_ref.namelist():
-            if file_path.endswith('components.json') and 'assets/external_comps/' in file_path:
-                with zip_ref.open(file_path) as file:
-                    components_json_content = file.read().decode('utf-8', errors='ignore')
-                    components_data = json.loads(components_json_content)
-                    for component in components_data:
-                        extension_type = component.get("type", "")
-                        if extension_type:
-                            extensions.append(extension_type)
-    return extensions
-
-def count_events_in_bky_file(bky_content):
-    
-    return bky_content.count('<block type="component_event"')
-
-def extract_app_name_from_scm_files(temp_dir):
-    scm_files = glob.glob(f"{temp_dir}/src/appinventor/*/*/*.scm")
-    for scm_file in scm_files:
-        with open(scm_file, 'r', encoding='utf-8', errors='ignore') as file:
-            content = file.read()
-
-            
-            regex_patterns = [
-                r'"AppName"\s*:\s*"([^"]+)"',
-                r'"AppName"\s*:\s*\'([^\']+)\''  
-            ]
-
-            for pattern in regex_patterns:
-                app_name_match = re.search(pattern, content)
-                if app_name_match:
-                    return app_name_match.group(1)
-
-    
-    print(f"Aviso: Nome do aplicativo não encontrado no diretório {temp_dir}")
-    return "N/A"
-
-def extract_project_info_from_properties(file_path):
-    
-    timestamp = "N/A"
-    app_name = "N/A"
-    app_version = "N/A"
-    authURL = "ai2.appinventor.mit.edu"
-
-    
-    with tempfile.TemporaryDirectory() as temp_dir:
-        with ZipFile(file_path, 'r') as zip_ref:
-            zip_ref.extractall(temp_dir)
-            
-            project_properties_file_path = 'youngandroidproject/project.properties'
-
-            
-            if project_properties_file_path in zip_ref.namelist():
-                with zip_ref.open(project_properties_file_path) as file:
-                    project_properties_lines = file.read().decode('utf-8').splitlines()
-
-                    
-                    timestamp = project_properties_lines[1] if len(project_properties_lines) > 1 else "N/A"
-
-                    
-                    for line in project_properties_lines:
-                        app_name_match = re.match(r'aname=(.*)', line)
-                        if app_name_match:
-                            app_name = app_name_match.group(1)
-
-                        app_version_match = re.match(r'versionname=(.*)', line)
-                        if app_version_match:
-                            app_version = app_version_match.group(1)
-
-        
-        if app_name == "N/A":
-         print("O campo App Name não foi encontrado em project.properties. Tentando encontrar em arquivos .scm...")
-        app_name = extract_app_name_from_scm_files(temp_dir)
-        print(f"Nome do App encontrado nos arquivos .scm: {app_name}")
-
-    # ...
-
+def calculate_basic_metrics(y, sr):
+    pitches, magnitudes = librosa.piptrack(y=y, sr=sr)
+    average_pitch = np.mean(pitches[pitches > 0])
+    mfccs = librosa.feature.mfcc(y=y, sr=sr)
+    energy = np.sum(y ** 2)
+    zero_crossing_rate = np.mean(librosa.feature.zero_crossing_rate(y))
+    spectral_centroid = np.mean(librosa.feature.spectral_centroid(y=y, sr=sr))
 
     return {
-        'timestamp': timestamp,
-        'app_name': app_name,
-        'app_version': app_version,
-        'authURL': authURL
+        'Average Pitch': average_pitch,
+        'Number of MFCCs': mfccs.shape[1],
+        'Energy': energy,
+        'Zero Crossing Rate': zero_crossing_rate,
+        'Spectral Centroid': spectral_centroid
     }
 
 
+def calculate_advanced_metrics(y, sr):
+    metrics = {}
 
+    f0, _, _ = librosa.pyin(y, fmin=50, fmax=4000)
+    if f0 is not None:
+        metrics['Average F0 (YIN)'] = np.nanmean(f0)
 
+    chroma = librosa.feature.chroma_stft(y=y, sr=sr)
+    metrics['Average Chroma'] = np.mean(chroma)
 
-def extract_ai_components(components):
-    ai_components = []
-    for component in components:
-        for pattern in ai_patterns:
-            if '*' in pattern and component.startswith(pattern[:-1]):
-                ai_components.append(component)
-            elif component == pattern:
-                ai_components.append(component)
-    if "roboflow" in ' '.join(components).lower():
-        ai_components.append("Using Roboflow")
-    return ai_components
-
-def extract_media_files(file_path: str):
-    media_files = []
-    with ZipFile(file_path, 'r') as zip_ref:
-        for file_path in zip_ref.namelist():
-            if 'assets/' in file_path and not file_path.endswith('/'):
-                media_files.append(os.path.basename(file_path))
-    return media_files
-
-def list_components_in_aia_file(file_path):
-    
-    results_df = pd.DataFrame(columns=[
-        'aia_file', 'project_info', 'components', 'IA components', 'screens', 'operators',
-        'variables', 'events', 'extensions', 'Media',
-        'Drawing and Animation', 'Maps', 'Sensors', 'Social', 'Storage', 'Connectivity'])
+    spectral_contrast = librosa.feature.spectral_contrast(y=y, sr=sr)
+    metrics['Average Spectral Contrast'] = np.mean(spectral_contrast)
 
- 
-    pd.set_option('display.max_colwidth', None)
-    file_name = os.path.basename(file_path)
-    
+    return metrics
 
-    components_list = []
-    number_of_screens = 0
-    operators_count = 0
-    variables_count = 0
-    events_count = 0 
-    
-    media_files = extract_media_files(file_path)
-    media_summary = ', '.join(media_files)
-    
-    project_info = extract_project_info_from_properties(file_path)
-    project_info_str = f"Timestamp: {project_info['timestamp']}, App Name: {project_info['app_name']}, Version: {project_info['app_version']}, AuthURL: {project_info['authURL']}"
 
+def generate_spectrogram(y, sr):
+    plt.figure(figsize=(10, 4))
+    librosa.display.specshow(librosa.amplitude_to_db(np.abs(librosa.stft(y)), ref=np.max), sr=sr, x_axis='time', y_axis='log')
+    plt.colorbar(format='%+2.0f dB')
+    plt.title('Spectrogram')
+    plt.tight_layout()
 
-    with tempfile.TemporaryDirectory() as temp_dir:
-        with ZipFile(file_path, 'r') as zip_ref:
-            zip_ref.extractall(temp_dir)
-        scm_files = glob.glob(temp_dir + '/src/appinventor/*/*/*.scm')
-        bky_files = glob.glob(temp_dir + '/src/appinventor/*/*/*.bky') 
 
-        number_of_screens = len(scm_files)
-        for scm_file in scm_files:
-            with open(scm_file, 'r', encoding='utf-8', errors='ignore') as file:
-                content = file.read()
-                components = extract_components_using_regex(content)
-                components_list.extend(components)
-                operators_count += len(re.findall(r'[+\-*/<>!=&|]', content))
-                variables_count += len(re.findall(r'"\$Name":"(.*?)"', content))
+    with tempfile.NamedTemporaryFile(delete=False, suffix='.png', mode='w+b') as f:
+        plt.savefig(f.name, format='png')
+        plt.close()
+        return f.name
 
-        
-        drawing_and_animation_summary = ', '.join(extract_category_components(components_list, drawing_and_animation_patterns))
-        maps_summary = ', '.join(extract_category_components(components_list, maps_patterns))
-        sensors_summary = ', '.join(extract_category_components(components_list, sensors_patterns))
-        social_summary = ', '.join(extract_category_components(components_list, social_patterns))
-        storage_summary = ', '.join(extract_category_components(components_list, storage_patterns))
-        connectivity_summary = ', '.join(extract_category_components(components_list, connectivity_patterns))
 
+def process_audio(file):
+    if file is None:
+        return {}, "placeholder.png"  
 
-        
-        
-        extensions_list = []
-        extensions_list = extract_extensions_from_aia(file_path)
+    sr, y = file
 
-        for bky_file in bky_files:
-            with open(bky_file, 'r', encoding='utf-8', errors='ignore') as file:
-                bky_content = file.read()
-                events_count += count_events_in_bky_file(bky_content)
-                
+    if y.dtype != np.float32:
+        y = y.astype(np.float32) / np.iinfo(y.dtype).max
 
+    basic_metrics = calculate_basic_metrics(y, sr)
+    advanced_metrics = calculate_advanced_metrics(y, sr)
 
-        
-        extensions_summary = ', '.join(list(set(extensions_list)))
+    metrics = {**basic_metrics, **advanced_metrics}
 
-    components_count = collections.Counter(components_list)
-    components_summary = [f'{comp} ({count} x)' if count > 1 else comp for comp, count in components_count.items()]
-    ai_components_summary = extract_ai_components(components_list)
-    new_row = pd.DataFrame([{
-    'aia_file': file_name,
-    'project_info': project_info_str,
-    'components': ', '.join(components_summary),
-    'IA components': ', '.join(ai_components_summary),
-    'screens': number_of_screens,
-    'operators': operators_count,
-    'variables': variables_count,
-    'events': events_count,
-    'extensions': extensions_summary,
-    'Media': media_summary,
-    'Drawing and Animation': drawing_and_animation_summary,
-    'Maps': maps_summary,
-    'Sensors': sensors_summary,
-    'Social': social_summary,
-    'Storage': storage_summary,
-    'Connectivity': connectivity_summary
-    }])
+    image_path = generate_spectrogram(y, sr)
 
-    
-    results_df = pd.concat([results_df, new_row], ignore_index=True)
-    return results_df
-#
-
-
-output_style = """
-<style>
-    .output-container {
-        max-height: 500px; /* Ajuste a altura máxima conforme necessário */
-        overflow: auto; /* Isso permite a rolagem vertical e horizontal se necessário */
-        display: block; /* Isso garante que o container seja renderizado abaixo do botão submit */
-    }
-    .output-container table {
-        width: 100%; /* Isso faz com que a tabela utilize toda a largura do container */
-        border-collapse: collapse;
-    }
-    .output-container th, .output-container td {
-        border: 1px solid #ddd; /* Isso adiciona bordas às células para melhor visualização */
-        text-align: left;
-        padding: 8px;
-    }
-</style>
-"""
+    return metrics, image_path
 
 
-def analyze_aia(uploaded_file):
-    try:
-        
-        file_path = uploaded_file.name if hasattr(uploaded_file, 'name') else None
-
-        if file_path and os.path.exists(file_path):
-            with ZipFile(file_path, 'r') as zip_ref:
-                with tempfile.TemporaryDirectory() as temp_dir:
-                    zip_ref.extractall(temp_dir)
-                    results_df = list_components_in_aia_file(file_path)
-                    
-                    html_result = results_df.to_html(escape=False, classes="output-html")
-                    return output_style + f'<div class="output-container">{html_result}</div>'
-
-
-        else:
-            return output_style + "Não foi possível localizar o arquivo .aia."
-
-    except BadZipFile:
-        return output_style + "Falha ao abrir o arquivo .aia como um arquivo zip. Ele pode estar corrompido ou não é um arquivo .aia válido."
-
-    except Exception as e:
-        return output_style + f"Erro ao processar o arquivo: {str(e)}"
-
 iface = gr.Interface(
-    fn=analyze_aia,
-    inputs=gr.File(),
-    outputs=gr.HTML(),
-    title="AIA-Scope",
-    description="Upload an .aia file to analyze its components.",
-    live=False  
+    fn=process_audio,
+    inputs=gr.Audio(label="Upload Audio"),
+    outputs=["json", "image"],
+    title="Speech-Scope",
+    description="Speech and audio Metrics Analysis"
 )
 
-if __name__ == "__main__":
-    iface.launch(debug=True)
-
-
-
+iface.launch(debug=True)

requirements.txt

@@ -1,3 +1,4 @@
 gradio
-pandas
-glob2 # se você estiver usando glob2
+librosa
+numpy
+matplotlib