File size: 1,707 Bytes
0f06115 1188ffd 0f06115 1188ffd 0f06115 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 |
import streamlit as st
import librosa
import soundfile as sf
import tempfile
import os
from utils.noise_removal import remove_noise
from utils.vad_segmentation import vad_segmentation
from utils.speaker_diarization import diarize_speakers
from utils.noise_classification import classify_noise
st.set_page_config(page_title="Audio Analyzer", layout="wide")
st.title(" Audio Analysis Pipeline")
uploaded_file = st.file_uploader("Upload an audio file", type=["wav", "mp3"])
if uploaded_file:
with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as tmp:
tmp.write(uploaded_file.read())
tmp_path = tmp.name
st.audio(tmp_path, format='audio/wav')
st.subheader("1️⃣ Noise Removal")
denoised_path = tmp_path.replace(".wav", "_denoised.wav")
remove_noise(tmp_path, denoised_path)
st.audio(denoised_path, format="audio/wav")
st.subheader("2️⃣ Speech Segmentation")
speech_segments = vad_segmentation(denoised_path)
st.write(f"Detected {len(speech_segments)} speech segments.")
for i, (start, end) in enumerate(speech_segments[:5]):
st.write(f"Segment {i+1}: {start:.2f}s to {end:.2f}s")
st.subheader("3️⃣ Speaker Diarization")
diarization = diarize_speakers(denoised_path)
st.text("Speakers detected:")
for turn, _, speaker in diarization.itertracks(yield_label=True):
st.write(f"{turn.start:.2f}s - {turn.end:.2f}s: {speaker}")
st.subheader("4️⃣ Noise Classification")
noise_predictions = classify_noise(denoised_path)
st.write("Top predicted noise classes:")
for cls, prob in noise_predictions:
st.write(f"{cls}: {prob:.2f}")
|