File size: 2,784 Bytes
fad9b18 ae33b95 fad9b18 ae33b95 fad9b18 ae33b95 307d0c6 ae33b95 307d0c6 ae33b95 fad9b18 ae33b95 fad9b18 307d0c6 fad9b18 307d0c6 fad9b18 307d0c6 fad9b18 307d0c6 fad9b18 |
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 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 |
import streamlit as st
import tempfile
import os
from pydub import AudioSegment
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", "m4a", "mp4a"])
def prepare_audio(uploaded_file):
file_ext = uploaded_file.name.split('.')[-1].lower()
with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as out_wav:
if file_ext == "wav":
out_wav.write(uploaded_file.read())
else:
audio = AudioSegment.from_file(uploaded_file, format=file_ext)
audio.export(out_wav.name, format="wav")
return out_wav.name
if uploaded_file:
st.audio(uploaded_file, format="audio/wav")
with st.spinner("🔄 Preparing audio..."):
tmp_path = prepare_audio(uploaded_file)
try:
st.subheader("1️⃣ Noise Removal")
denoised_path = tmp_path.replace(".wav", "_denoised.wav")
with st.spinner("Removing noise..."):
remove_noise(tmp_path, denoised_path)
st.audio(denoised_path, format="audio/wav")
except Exception as e:
st.error(f" Noise removal failed: {e}")
try:
st.subheader("2️⃣ Speech Segmentation")
with st.spinner("Running Voice Activity Detection..."):
speech_annotation = vad_segmentation(denoised_path)
segments = [(seg.start, seg.end) for seg in speech_annotation.itersegments()]
st.write(f" Detected {len(segments)} speech segments.")
for i, (start, end) in enumerate(segments[:5]):
st.write(f"Segment {i+1}: {start:.2f}s to {end:.2f}s")
except Exception as e:
st.error(f" VAD failed: {e}")
try:
st.subheader("3️⃣ Speaker Diarization")
with st.spinner("Diarizing speakers..."):
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 {speaker}")
except Exception as e:
st.error(f"Speaker diarization failed: {e}")
try:
st.subheader("4️⃣ Noise Classification")
with st.spinner("Classifying background noise..."):
noise_predictions = classify_noise(denoised_path)
st.write("Top predicted noise classes:")
for cls, prob in noise_predictions:
st.write(f"{cls}: {prob:.2f}")
except Exception as e:
st.error(f"Noise classification failed: {e}")
|