146 lines
5.4 KiB
Python
146 lines
5.4 KiB
Python
import tempfile
|
|
from pathlib import Path
|
|
|
|
import joblib
|
|
import streamlit as st
|
|
|
|
from audio_utils import SUPPORTED_AUDIO_EXTENSIONS, convert_to_wav
|
|
from features import LABEL_PD, LABEL_TPD, extract_features
|
|
|
|
|
|
BASE_DIR = Path(__file__).resolve().parent
|
|
MODEL_PATH = BASE_DIR / "models" / "svm_voice_confidence_model.joblib"
|
|
CONFIDENCE_THRESHOLD = 0.75
|
|
MARGIN_THRESHOLD = 0.25
|
|
SUPPORTED_UPLOAD_TYPES = [extension.replace(".", "") for extension in sorted(SUPPORTED_AUDIO_EXTENSIONS)]
|
|
|
|
LABEL_DESCRIPTION = {
|
|
LABEL_PD: "Percaya Diri",
|
|
LABEL_TPD: "Tidak Percaya Diri",
|
|
}
|
|
|
|
|
|
@st.cache_resource
|
|
def load_model(model_mtime):
|
|
"""
|
|
model_mtime menjadi cache key.
|
|
Jika model dilatih ulang, Streamlit otomatis memuat model terbaru.
|
|
"""
|
|
return joblib.load(MODEL_PATH)
|
|
|
|
|
|
def save_uploaded_file(uploaded_file, suffix):
|
|
with tempfile.NamedTemporaryFile(delete=False, suffix=suffix) as temp_audio:
|
|
temp_audio.write(uploaded_file.getbuffer())
|
|
return Path(temp_audio.name)
|
|
|
|
|
|
def predict_uploaded_audio(uploaded_file):
|
|
"""
|
|
Alur prediksi:
|
|
upload audio -> convert WAV mono 22050 Hz -> extract_features -> scaler+SVM pipeline.
|
|
"""
|
|
model = load_model(MODEL_PATH.stat().st_mtime)
|
|
original_extension = Path(uploaded_file.name).suffix.lower()
|
|
|
|
if original_extension not in SUPPORTED_AUDIO_EXTENSIONS:
|
|
allowed = ", ".join(SUPPORTED_UPLOAD_TYPES).upper()
|
|
raise ValueError(f"Format file tidak didukung. Gunakan salah satu: {allowed}")
|
|
|
|
temp_input_path = save_uploaded_file(uploaded_file, original_extension)
|
|
temp_wav_path = Path(tempfile.NamedTemporaryFile(delete=False, suffix=".wav").name)
|
|
|
|
try:
|
|
convert_to_wav(temp_input_path, temp_wav_path)
|
|
feature_vector = extract_features(temp_wav_path)
|
|
features = feature_vector.reshape(1, -1)
|
|
|
|
expected_features = model.named_steps["scaler"].n_features_in_
|
|
if features.shape[1] != expected_features:
|
|
raise ValueError(
|
|
"Jumlah fitur audio tidak sesuai dengan model. "
|
|
f"Audio menghasilkan {features.shape[1]} fitur, "
|
|
f"sedangkan model mengharapkan {expected_features}. "
|
|
"Jalankan ulang `python train_model.py`, lalu restart Streamlit."
|
|
)
|
|
probabilities = model.predict_proba(features)[0]
|
|
class_probabilities = dict(zip(model.classes_, probabilities))
|
|
|
|
predicted_label = max(class_probabilities, key=class_probabilities.get)
|
|
confidence = class_probabilities[predicted_label]
|
|
|
|
probability_pd = class_probabilities.get(LABEL_PD, 0.0)
|
|
probability_tpd = class_probabilities.get(LABEL_TPD, 0.0)
|
|
margin = abs(probability_pd - probability_tpd)
|
|
|
|
debug_info = {
|
|
"model_classes": list(model.classes_),
|
|
"raw_probabilities": probabilities.tolist(),
|
|
"feature_shape": features.shape,
|
|
"confidence": float(confidence),
|
|
"margin": float(margin),
|
|
}
|
|
finally:
|
|
temp_input_path.unlink(missing_ok=True)
|
|
temp_wav_path.unlink(missing_ok=True)
|
|
|
|
return predicted_label, confidence, class_probabilities, debug_info
|
|
|
|
|
|
st.set_page_config(
|
|
page_title="Klasifikasi Percaya Diri dari Suara",
|
|
layout="centered",
|
|
)
|
|
|
|
st.title("Klasifikasi Percaya Diri dari Suara")
|
|
st.write("Upload file audio untuk memprediksi kelas PD atau TPD.")
|
|
|
|
if not MODEL_PATH.exists():
|
|
st.error("Model belum ditemukan. Jalankan `python train_model.py` terlebih dahulu.")
|
|
st.stop()
|
|
|
|
uploaded_file = st.file_uploader(
|
|
"Pilih file audio",
|
|
type=SUPPORTED_UPLOAD_TYPES,
|
|
)
|
|
|
|
if uploaded_file is not None:
|
|
uploaded_extension = Path(uploaded_file.name).suffix.lower().replace(".", "")
|
|
st.audio(uploaded_file, format=f"audio/{uploaded_extension}")
|
|
|
|
if st.button("Prediksi"):
|
|
with st.spinner("Mengekstraksi fitur dan memprediksi..."):
|
|
try:
|
|
label, confidence, probabilities, debug_info = predict_uploaded_audio(uploaded_file)
|
|
except Exception as error:
|
|
st.error(f"Gagal memproses audio: {error}")
|
|
st.stop()
|
|
|
|
probability_pd = probabilities.get(LABEL_PD, 0.0)
|
|
probability_tpd = probabilities.get(LABEL_TPD, 0.0)
|
|
margin = abs(probability_pd - probability_tpd)
|
|
|
|
st.subheader("Hasil Prediksi")
|
|
st.write(f"Prediksi: {label}")
|
|
st.write(f"Keterangan: {LABEL_DESCRIPTION[label]}")
|
|
st.write(f"Confidence: {confidence * 100:.2f}%")
|
|
st.write(f"Probabilitas PD: {probability_pd * 100:.2f}%")
|
|
st.write(f"Probabilitas TPD: {probability_tpd * 100:.2f}%")
|
|
|
|
if confidence >= CONFIDENCE_THRESHOLD and margin >= MARGIN_THRESHOLD:
|
|
st.success(f"Hasil utama: {label} - {LABEL_DESCRIPTION[label]}")
|
|
else:
|
|
st.warning("Model belum cukup yakin, silakan rekam ulang atau tambah data training.")
|
|
|
|
st.progress(float(probability_pd), text=f"PD: {probability_pd * 100:.2f}%")
|
|
st.progress(float(probability_tpd), text=f"TPD: {probability_tpd * 100:.2f}%")
|
|
|
|
with st.expander("Debug prediksi"):
|
|
st.write("model.classes_")
|
|
st.json(debug_info["model_classes"])
|
|
st.write("Probabilitas mentah dari predict_proba")
|
|
st.json(debug_info["raw_probabilities"])
|
|
st.write(f"Fitur audio shape: {debug_info['feature_shape']}")
|
|
st.write(f"Confidence: {debug_info['confidence']:.6f}")
|
|
st.write(f"Margin probabilitas: {debug_info['margin']:.6f}")
|