Upload 2 files

app.py

@@ -0,0 +1,133 @@
+
+import gradio as gr
+from transformers import pipeline
+import whisper
+from collections import Counter
+import matplotlib.pyplot as plt
+
+# Load models
+emotion_classifier = pipeline("audio-classification", model="superb/hubert-large-superb-er")
+whisper_model = whisper.load_model("base")
+
+# Chart generator
+def create_emotion_chart(labels, scores):
+    emoji_map = {
+        "hap": "😊 Happy", "sad": "😔 Sad", "neu": "😐 Neutral",
+        "ang": "😠 Angry", "fea": "😨 Fear", "dis": "🤢 Disgust", "sur": "😮 Surprise"
+    }
+    color_map = {
+        "hap": "#facc15", "sad": "#60a5fa", "neu": "#a1a1aa",
+        "ang": "#ef4444", "fea": "#818cf8", "dis": "#14b8a6", "sur": "#f472b6"
+    }
+    labels = [emoji_map.get(label, label) for label in labels]
+    colors = [color_map.get(label, "#60a5fa") for label in labels]
+
+    fig, ax = plt.subplots(figsize=(5, 3.5))
+    bars = ax.barh(labels, scores, color=colors, edgecolor="black", height=0.5)
+    for bar, score in zip(bars, scores):
+        ax.text(bar.get_width() + 0.02, bar.get_y() + bar.get_height() / 2,
+                f"{score:.2f}", va='center', fontsize=10, color='black')
+    ax.set_xlim(0, 1)
+    ax.set_title("🎭 Emotion Confidence Scores", fontsize=13, pad=10)
+    ax.invert_yaxis()
+    ax.set_facecolor("#f9fafb")
+    fig.patch.set_facecolor("#f9fafb")
+    for spine in ax.spines.values():
+        spine.set_visible(False)
+    ax.tick_params(axis='x', colors='gray')
+    ax.tick_params(axis='y', colors='gray')
+    return fig
+
+def generate_next_moves(dominant_emotion, conf_score, transcript=""):
+    suggestions = []
+    harsh_words = ["bad", "ugly", "terrible", "hate", "worst"]
+    positive_tone_negative_words = any(word in transcript.lower() for word in harsh_words) if "happiness" in dominant_emotion else False
+
+    if 'sadness' in dominant_emotion:
+        suggestions.append("Your tone feels low — try lifting the pitch slightly to bring more warmth.")
+        suggestions.append("Even if the words are positive, a brighter tone helps convey enthusiasm.")
+    elif 'happiness' in dominant_emotion and conf_score >= 80:
+        suggestions.append("Nice energy! Try modulating your tone even more for emphasis in key moments.")
+        suggestions.append("Experiment with subtle emotional shifts as you speak for more depth.")
+    elif 'neutral' in dominant_emotion:
+        suggestions.append("Add inflection to break a monotone pattern — especially at the ends of sentences.")
+        suggestions.append("Highlight your message by stressing emotionally important words.")
+    elif conf_score < 50:
+        suggestions.append("Try exaggerating vocal ups and downs when reading to unlock more expression.")
+        suggestions.append("Slow down slightly and stretch certain words to vary your delivery.")
+    else:
+        suggestions.append("Keep practicing tone variation — you’re building a solid base.")
+
+    if positive_tone_negative_words:
+        suggestions.append("Your tone was upbeat, but the word choices were harsh — aim to align both for better impact.")
+    return "\n- " + "\n- ".join(suggestions)
+
+def generate_personacoach_report(emotions, transcript):
+    report = "## 📝 Your PersonaCoach Report\n---\n\n"
+    report += "### 🗒️ What You Said:\n"
+    report += f"> _{transcript.strip()}_\n\n"
+
+    label_map = {
+        'hap': '😊 happiness', 'sad': '😔 sadness', 'neu': '😐 neutral',
+        'ang': '😠 anger', 'fea': '😨 fear', 'dis': '🤢 disgust', 'sur': '😮 surprise'
+    }
+    for e in emotions:
+        e['emotion'] = label_map.get(e['label'], e['label'])
+
+    scores = [e['score'] for e in emotions]
+    top_score = max(scores)
+    conf_score = int(top_score * 100)
+
+    emotion_labels = [e['emotion'] for e in emotions if e['score'] >= 0.2]
+    dominant_emotion = emotion_labels[0] if emotion_labels else "neutral"
+
+    report += f"### 🎯 Tone Strength:\n- Your tone scored **{conf_score}/100** in clarity.\n\n"
+    report += "### 🗣️ Emotion & Delivery:\n"
+    if emotion_labels:
+        emo_str = ", ".join([f"{e['emotion']} ({e['score']:.2f})" for e in emotions])
+        report += f"- Emotionally, your voice showed: {emo_str}\n"
+    else:
+        report += "- Your tone wasn’t clearly expressive. Try reading with a bit more emphasis or emotion.\n"
+
+    filler_words = ["um", "uh", "like", "you know", "so", "actually", "basically", "literally"]
+    words = transcript.lower().split()
+    total_words = len(words)
+    filler_count = sum(words.count(fw) for fw in filler_words)
+    filler_ratio = filler_count / total_words if total_words > 0 else 0
+
+    report += "\n### 💬 Pausing Style:\n"
+    report += f"- {filler_count} fillers out of {total_words} words.\n"
+    if filler_ratio > 0.06:
+        report += "- Try pausing instead of fillers.\n"
+    elif filler_ratio > 0.03:
+        report += "- A few fillers — consider tightening up delivery.\n"
+    else:
+        report += "- Strong fluency — great control.\n"
+
+    report += "\n### 🧭 Next Moves:\n"
+    report += generate_next_moves(dominant_emotion, conf_score, transcript)
+    return report
+
+def analyze_audio(audio_path):
+    result = whisper_model.transcribe(audio_path)
+    transcript = result['text']
+    emotion_results = emotion_classifier(audio_path)
+    labels = [r['label'] for r in emotion_results]
+    scores = [r['score'] for r in emotion_results]
+    fig = create_emotion_chart(labels, scores)
+    report = generate_personacoach_report(emotion_results, transcript)
+    return transcript, fig, report
+
+interface = gr.Interface(
+    fn=analyze_audio,
+    inputs=gr.Audio(type="filepath", label="Upload your voice (.wav only)"),
+    outputs=[
+        gr.Textbox(label="📝 Transcription"),
+        gr.Plot(label="🎭 Emotion Chart"),
+        gr.Markdown(label="📄 PersonaCoach Feedback")
+    ],
+    title="SPEAK – Speech Performance Evaluation and Affective Knowledge",
+    description="Upload a voice sample and get coaching feedback on tone, emotion, and fluency."
+)
+
+interface.launch()

requirements.txt

@@ -0,0 +1,7 @@
+
+gradio
+matplotlib
+torch
+transformers
+librosa
+openai-whisper