| import streamlit as st |
| import os |
| import tempfile |
| import requests |
| import random |
| import matplotlib.pyplot as plt |
| import torchaudio |
| import torch |
| import ffmpeg |
|
|
| |
| try: |
| from speechbrain.inference import EncoderClassifier |
| classifier = EncoderClassifier.from_hparams( |
| source="speechbrain/lang-id-commonlanguage_ecapa", |
| savedir="pretrained_models/lang-id-commonlanguage_ecapa" |
| ) |
| SB_READY = True |
| except Exception as e: |
| st.warning(" SpeechBrain model load failed. Falling back to simulation.") |
| SB_READY = False |
|
|
| |
| accent_profiles = { |
| "American": ["rhotic", "flapped_t", "cot_caught_merger"], |
| "British": ["non_rhotic", "t_glottalization", "trap_bath_split"], |
| "Australian": ["non_rhotic", "flat_a", "high_rising_terminal"], |
| "Canadian": ["rhotic", "canadian_raising", "eh_tag"], |
| "Indian": ["retroflex_consonants", "monophthongization", "syllable_timing"] |
| } |
|
|
| def simulate_accent_classification(): |
| accent = random.choice(list(accent_profiles.keys())) |
| confidence = random.uniform(75, 98) |
| return { |
| "accent": accent, |
| "confidence": round(confidence, 2), |
| "summary": f"Simulated detection: {accent} accent with {confidence:.2f}% confidence." |
| } |
|
|
| def real_accent_classification(audio_path): |
| try: |
| signal, sr = torchaudio.load(audio_path) |
| if signal.shape[0] > 1: |
| signal = signal.mean(dim=0, keepdim=True) |
| if sr != 16000: |
| signal = torchaudio.transforms.Resample(sr, 16000)(signal) |
| signal = signal.unsqueeze(0) |
|
|
| pred = classifier.classify_batch(signal) |
| probs = pred[0].squeeze(0).tolist() |
| labels = pred[1][0] |
|
|
| lang_scores = {classifier.hparams.label_encoder.ind2lab[i]: p * 100 for i, p in enumerate(probs)} |
| top_lang = max(lang_scores, key=lang_scores.get) |
|
|
| if top_lang != "en": |
| return {"accent": "Non-English", "confidence": lang_scores[top_lang], "summary": f"Detected language: {top_lang}"} |
|
|
| |
| result = simulate_accent_classification() |
| result["summary"] += f" (Base language: English)" |
| return result |
| except Exception as e: |
| return simulate_accent_classification() |
|
|
| def extract_audio(url_or_file, is_upload=False): |
| temp_dir = tempfile.mkdtemp() |
| video_path = os.path.join(temp_dir, "input_video.mp4") |
| audio_path = os.path.join(temp_dir, "audio.wav") |
|
|
| if is_upload: |
| with open(video_path, "wb") as f: |
| f.write(url_or_file.read()) |
| else: |
| with requests.get(url_or_file, stream=True) as r: |
| r.raise_for_status() |
| with open(video_path, 'wb') as f: |
| for chunk in r.iter_content(chunk_size=8192): |
| f.write(chunk) |
|
|
| ffmpeg.input(video_path).output(audio_path, ar=16000, ac=1).run(overwrite_output=True, quiet=True) |
| return audio_path |
|
|
| |
| st.set_page_config(page_title="English Accent Analyzer", layout="centered") |
| st.title("🗣️ English Accent Analyzer") |
|
|
| st.markdown("### 🎯 Objective:\nUpload or link a video/audio of a speaker. We’ll detect if they're speaking English and simulate the accent.") |
|
|
| url_input = st.text_input("🔗 Paste public Loom or direct MP4/WAV link:") |
| uploaded_file = st.file_uploader("📁 Or upload a video/audio file", type=["mp4", "wav"]) |
|
|
| if st.button(" Analyze"): |
| if not url_input and not uploaded_file: |
| st.error("Please provide a valid URL or upload a file.") |
| else: |
| with st.spinner("Analyzing..."): |
| try: |
| audio_path = extract_audio(uploaded_file if uploaded_file else url_input, is_upload=bool(uploaded_file)) |
| result = real_accent_classification(audio_path) if SB_READY else simulate_accent_classification() |
|
|
| st.success(f"🎧 Detected Accent: **{result['accent']}**") |
| st.metric("Confidence", f"{result['confidence']}%") |
| st.markdown(f"📝 {result['summary']}") |
| except Exception as e: |
| st.error(f"❌ Error during analysis: {e}") |
|
|
