MIF_E31231708/ml/app.py

313 lines
11 KiB
Python

from datetime import datetime
import tempfile
from pathlib import Path
import joblib
import librosa
import numpy as np
import streamlit as st
from audio_utils import SUPPORTED_AUDIO_EXTENSIONS, convert_to_wav
from features import LABEL_PD, LABEL_TPD, SAMPLE_RATE, extract_features
BASE_DIR = Path(__file__).resolve().parent
DATA_DIR = BASE_DIR / "data"
MODEL_PATH = BASE_DIR / "models" / "svm_voice_confidence_model.joblib"
CONFIDENCE_THRESHOLD = 0.75
MARGIN_THRESHOLD = 0.25
MIN_RECORDING_DURATION_SECONDS = 2.0
LOW_RMS_WARNING_THRESHOLD = 0.003
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_bytes_to_temp_file(audio_bytes, suffix):
with tempfile.NamedTemporaryFile(delete=False, suffix=suffix) as temp_audio:
temp_audio.write(audio_bytes)
return Path(temp_audio.name)
def save_uploaded_file(uploaded_file, suffix):
return save_bytes_to_temp_file(uploaded_file.getvalue(), suffix)
def validate_audio_quality(audio_path, min_duration=MIN_RECORDING_DURATION_SECONDS):
"""
Validasi dasar sebelum ekstraksi fitur.
Error dipakai untuk kasus file kosong/gagal dibaca/terlalu pendek.
Warning dipakai untuk audio yang masih bisa diproses tetapi kualitasnya lemah.
"""
try:
y, sr = librosa.load(audio_path, sr=SAMPLE_RATE, mono=True)
except Exception as error:
raise ValueError(f"File audio gagal dibaca: {error}") from error
if y.size == 0:
raise ValueError("File audio kosong atau tidak memiliki sinyal suara.")
duration = librosa.get_duration(y=y, sr=sr)
if duration < min_duration:
raise ValueError(
f"Durasi audio terlalu pendek ({duration:.2f} detik). "
"Silakan rekam suara 3 sampai 5 detik dengan jelas."
)
rms = float(np.sqrt(np.mean(y**2)))
warning = None
if rms < LOW_RMS_WARNING_THRESHOLD:
warning = (
f"Suara terdeteksi cukup pelan (RMS={rms:.5f}). "
"Jika hasil kurang tepat, rekam ulang dengan suara lebih jelas."
)
return {
"duration": duration,
"rms": rms,
"warning": warning,
}
def predict_audio_path(audio_path, validate_quality=True):
"""
Fungsi prediksi umum untuk upload dan rekaman.
Urutan:
audio_path -> convert_to_wav -> validate -> extract_features -> predict_proba.
Label utama diambil dari probabilitas terbesar, bukan model.predict().
"""
model = load_model(MODEL_PATH.stat().st_mtime)
audio_path = Path(audio_path)
extension = audio_path.suffix.lower()
if extension not in SUPPORTED_AUDIO_EXTENSIONS:
allowed = ", ".join(SUPPORTED_UPLOAD_TYPES).upper()
raise ValueError(f"Format file tidak didukung. Gunakan salah satu: {allowed}")
temp_wav_path = Path(tempfile.NamedTemporaryFile(delete=False, suffix=".wav").name)
try:
convert_to_wav(audio_path, temp_wav_path)
quality_info = validate_audio_quality(temp_wav_path) if validate_quality else None
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),
"quality_info": quality_info,
}
finally:
temp_wav_path.unlink(missing_ok=True)
return predicted_label, confidence, class_probabilities, debug_info
def render_prediction_result(label, confidence, probabilities, debug_info):
probability_pd = probabilities.get(LABEL_PD, 0.0)
probability_tpd = probabilities.get(LABEL_TPD, 0.0)
margin = abs(probability_pd - probability_tpd)
quality_info = debug_info.get("quality_info")
if quality_info and quality_info.get("warning"):
st.warning(quality_info["warning"])
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}%")
st.write(f"Margin: {margin * 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}")
if quality_info:
st.write(f"Durasi audio: {quality_info['duration']:.2f} detik")
st.write(f"RMS audio: {quality_info['rms']:.6f}")
def get_audio_recorder_input():
"""
Menggunakan st.audio_input jika tersedia.
Jika belum tersedia, coba fallback ke streamlit-mic-recorder.
"""
if hasattr(st, "audio_input"):
return st.audio_input("Rekam suara")
try:
from streamlit_mic_recorder import mic_recorder
except ImportError:
st.error(
"Versi Streamlit ini belum mendukung st.audio_input. "
"Install fallback recorder dengan perintah: pip install streamlit-mic-recorder"
)
return None
audio = mic_recorder(
start_prompt="Mulai Rekam",
stop_prompt="Berhenti Rekam",
just_once=False,
use_container_width=True,
key="mic_recorder",
)
if audio and audio.get("bytes"):
suffix = ".wav"
return {
"bytes": audio["bytes"],
"suffix": suffix,
"mime_type": "audio/wav",
}
return None
def get_recording_bytes(recording):
if recording is None:
return None, ".wav", "audio/wav"
if isinstance(recording, dict):
return recording["bytes"], recording.get("suffix", ".wav"), recording.get("mime_type", "audio/wav")
suffix = Path(recording.name).suffix.lower() or ".wav"
return recording.getvalue(), suffix, recording.type or "audio/wav"
def save_recording_to_dataset(source_audio_path, label):
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
target_dir = DATA_DIR / label
target_dir.mkdir(parents=True, exist_ok=True)
target_path = target_dir / f"recorded_{label}_{timestamp}.wav"
convert_to_wav(source_audio_path, target_path)
return target_path
st.set_page_config(
page_title="Klasifikasi Percaya Diri dari Suara",
layout="centered",
)
st.title("Klasifikasi Percaya Diri dari Suara")
st.write("Input audio, ekstraksi fitur, prediksi SVM, lalu tampilkan PD atau TPD.")
if not MODEL_PATH.exists():
st.error("Model belum ditemukan. Jalankan `python train_model.py` terlebih dahulu.")
st.stop()
upload_tab, record_tab = st.tabs(["Upload Audio", "Rekam Audio"])
with upload_tab:
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 Upload"):
temp_input_path = save_uploaded_file(uploaded_file, Path(uploaded_file.name).suffix.lower())
try:
with st.spinner("Mengekstraksi fitur dan memprediksi..."):
label, confidence, probabilities, debug_info = predict_audio_path(temp_input_path)
render_prediction_result(label, confidence, probabilities, debug_info)
except Exception as error:
st.error(f"Gagal memproses audio: {error}")
finally:
temp_input_path.unlink(missing_ok=True)
with record_tab:
st.write(
"Silakan rekam suara selama 3-5 detik. Gunakan suara yang jelas, "
"tidak terlalu pelan, dan hindari noise ruangan."
)
recording = get_audio_recorder_input()
audio_bytes, suffix, mime_type = get_recording_bytes(recording)
if audio_bytes:
st.audio(audio_bytes, format=mime_type)
temp_recording_path = save_bytes_to_temp_file(audio_bytes, suffix)
st.session_state["latest_recording_path"] = str(temp_recording_path)
if st.button("Prediksi Rekaman"):
try:
with st.spinner("Mengekstraksi fitur dan memprediksi rekaman..."):
label, confidence, probabilities, debug_info = predict_audio_path(temp_recording_path)
render_prediction_result(label, confidence, probabilities, debug_info)
except Exception as error:
st.error(f"Gagal memproses rekaman: {error}")
st.divider()
st.subheader("Simpan Rekaman ke Dataset")
selected_label = st.selectbox(
"Label manual",
options=[LABEL_PD, LABEL_TPD],
format_func=lambda label: f"{label} - {LABEL_DESCRIPTION[label]}",
)
if st.button("Simpan ke Dataset"):
try:
saved_path = save_recording_to_dataset(temp_recording_path, selected_label)
st.success(
"Rekaman berhasil disimpan. Jalankan ulang train_model.py "
"untuk melatih ulang model."
)
st.write(f"File: {saved_path}")
except Exception as error:
st.error(f"Gagal menyimpan rekaman ke dataset: {error}")