Update app.py

app.py

@@ -1,21 +1,15 @@
-import os
+import gradio as gr
 import subprocess
-import soundfile as sf
+import os
 import librosa
 from transformers import pipeline
-from datetime import datetime
 
-# Initialize Hugging Face pipeline
 classifier = pipeline(
     "audio-classification",
-    model="padmalcom/wav2vec2-large-nonverbalvocalization-classification",
+    model="padmalcom/wav2vec2-large-nonverbalvocalization-classification"
 )
 
 def convert_audio(input_path, output_path="input.wav"):
-    """Convert audio to 16kHz mono WAV using ffmpeg."""
-    if not os.path.isfile(input_path):
-        raise FileNotFoundError(f"File not found: {input_path}")
-    
     cmd = [
         "ffmpeg", "-i", input_path,
         "-acodec", "pcm_s16le",
@@ -24,23 +18,11 @@ def convert_audio(input_path, output_path="input.wav"):
         output_path,
         "-y"
     ]
+    subprocess.run(cmd, check=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+    return output_path
 
-    try:
-        subprocess.run(cmd, check=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
-        return output_path
-    except subprocess.CalledProcessError as e:
-        raise RuntimeError("FFmpeg conversion failed: " + e.stderr.decode())
-
-def detect_scream(audio_path: str):
-    """Run scream detection on a WAV file."""
-    if not os.path.isfile(audio_path):
-        raise FileNotFoundError(f"Audio file not found: {audio_path}")
-
-    audio, sr = sf.read(audio_path)
-    # Resample if needed
-    if sr != classifier.feature_extractor.sampling_rate:
-        audio = librosa.resample(audio, orig_sr=sr, target_sr=classifier.feature_extractor.sampling_rate)
-
+def detect_scream(audio_path):
+    audio, sr = librosa.load(audio_path, sr=16000)
     results = classifier(audio)
     top = results[0]
     label = top["label"]
@@ -53,27 +35,20 @@ def detect_scream(audio_path: str):
     else:
         alert = "None"
 
-    return label, score, alert
-
-def log_to_salesforce(audio_url, label, score, alert):
-    """Placeholder for Salesforce integration."""
-    print("Logging to Salesforce...")
-    print(f"Audio URL: {audio_url}")
-    print(f"Result: {label}, Score: {score:.1f}%, Alert Level: {alert}")
-    # Integration with Salesforce via simple-salesforce or REST API goes here
+    return f"Detected: {label} ({score:.1f}%) — Alert Level: {alert}"
 
-def main():
-    # Input file path (any audio format)
-    raw_input_path = "my_audio.mp3"  # Change to your input file
-    audio_url = "https://yourstorage.com/path/to/audio"  # Simulated URL
+def process_uploaded(audio_file):
+    # audio_file is a temp file path from gradio
+    wav_path = convert_audio(audio_file.name)
+    return detect_scream(wav_path)
 
-    try:
-        wav_path = convert_audio(raw_input_path)
-        label, score, alert = detect_scream(wav_path)
-        print(f"Detected: {label} ({score:.1f}%) — Alert Level: {alert}")
-        log_to_salesforce(audio_url, label, score, alert)
-    except Exception as e:
-        print("Error:", str(e))
+iface = gr.Interface(
+    fn=process_uploaded,
+    inputs=gr.Audio(type="filepath"),
+    outputs="text",
+    title="Scream Detection",
+    description="Upload an audio clip, and this app detects if it contains a scream."
+)
 
 if __name__ == "__main__":
-    main()
+    iface.launch()