voice-processing

app.py

@@ -1,7 +1,7 @@
-from faceVerificationUtilization import FaceValidation, FaceRecord, Recognize
+from faceVerificationUtilization import FaceValidation, FaceRecord, Recognize, UploadVoice
 import gradio as gr
 
-with gr.Blocks() as demo:
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
     with gr.Tabs():
         with gr.Tab("Face Validation"):
             gr.Markdown("## Cek validasi wajah")
@@ -34,7 +34,7 @@ with gr.Blocks() as demo:
             b3.click(fn=lambda img, n: FaceRecord(img, n, 3), inputs=[webcam, name], outputs=status3)
             b4.click(fn=lambda img, n: FaceRecord(img, n, 4), inputs=[webcam, name], outputs=status4)
 
-        with gr.Tab("Who Are You"):
+        with gr.Tab("Face Recognition"):
             gr.Markdown("## Cek Siapa Anda")
             gr.Interface(
                 fn=Recognize,
@@ -43,5 +43,44 @@ with gr.Blocks() as demo:
                 live=True
             )
 
+        with gr.Tab("Voice Processing"):
+            with gr.Row():
+                with gr.Column(scale=1):
+                    gr.Markdown("## 🎤 Voice Recorder (.wav)")
+                    gr.Markdown("Rekam suara Anda lalu otomatis diunggah ke **n8n** untuk transkripsi & ringkasan.")
+
+                    # komponen input rekaman
+                    audio_input = gr.Audio(
+                        sources=["microphone"], 
+                        type="filepath", 
+                        label="🎙️ Rekam Suara",
+                        show_download_button=True
+                    )
+
+                    # tombol upload
+                    submit_btn = gr.Button("⏫ Stop & Upload", variant="primary")
+
+                    # status
+                    status = gr.Label(label="Status")
+
+                with gr.Column(scale=1):
+                    # hasil transkripsi & ringkasan
+                    transcription = gr.Textbox(
+                        label="📄 Hasil Transkripsi", 
+                        interactive=False, 
+                        lines=5
+                    )
+                    summary = gr.Textbox(
+                        label="📝 Ringkasan", 
+                        interactive=False, 
+                        lines=5
+                    )
+
+            submit_btn.click(
+                UploadVoice,
+                inputs=audio_input,
+                outputs=[status, transcription, summary]
+            )
+
 if __name__ == "__main__":
     demo.launch()

faceVerificationUtilization/__init__.py

@@ -1 +1 @@
-from .utils import FaceValidation, FaceRecord, Recognize
+from .utils import FaceValidation, FaceRecord, Recognize, UploadVoice

faceVerificationUtilization/utils.py

@@ -5,6 +5,7 @@ import torch
 import pandas as pd
 from .setConfig import efficientnet_model, face_detector, transform, pca_xgb, faiss, load_db
 import os
+import requests
 
 def ImgPreprocessing(img):
     if len(img.shape) == 2 or img.shape[2] == 1:
@@ -58,6 +59,8 @@ def FaceValidationPredict(**face_crop):
 
     return pred, features, face_crop
 
+
+# feature
 def FaceValidation(frame: np.ndarray):
     if frame is None:
         return "No frame captured from webcam"
@@ -150,8 +153,31 @@ def Recognize(frame: np.ndarray):
     score = float(D[0][0])
     idx = int(I[0][0])
 
-    if score < 0.65:  
+    if score < 0.7:  
         return f"Tidak dikenali"
     else:
         return f"Terkenali sebagai: {labels[idx]} - (score={score:.2f})"
     
+def UploadVoice(audio_file):
+    if audio_file is None:
+        return "❌ Tidak ada file audio. Coba rekam lagi.", "", ""
+
+    try:
+        with open(audio_file, "rb") as f:
+            files = {"file": ("recording.wav", f, "audio/wav")}
+            response = requests.post("https://n8n.smartid.or.id/webhook/voice-upload", files=files)
+
+        if response.status_code != 200:
+            return f"❌ Gagal upload. Status: {response.status_code}", "", ""
+       
+        try:
+            data = response.json()  
+        except Exception:
+            return f"❌ Server tidak mengirim JSON. Balasan:\n{response}", "", ""
+    
+        transcription = data.get("transcribe", "(Tidak ada transkripsi)")
+        summary = data.get("summary", "(Tidak ada ringkasan)")
+
+        return "✅ Rekaman berhasil diproses", f"Transcribe: {transcription}", f"Summary: {summary}"
+    except Exception as e:
+        return f"❌ Gagal upload: {e}.", f"Transcribe: ", f"Summary: "