Update app.py

app.py

@@ -1,238 +1,42 @@
-import gradio as gr
-import openai
-from openai import OpenAI
-import os
-import uuid
-from gtts import gTTS
-from faster_whisper import WhisperModel
-import subprocess
-import shutil
-from datetime import datetime
-from sqlmodel import SQLModel, Field, create_engine, Session, select
-from typing import Optional
-import glob
-import re
-import matplotlib.pyplot as plt
-import io
-import base64
-from PIL import Image
-
-# === Temp file cleanup ===
-for pattern in ["/tmp/*.wav", "/tmp/*.mp3"]:
-    for filepath in glob.glob(pattern):
-        try:
-            os.remove(filepath)
-        except Exception as e:
-            print(f"Could not delete {filepath}: {e}")
-
-# === Environment setup ===
-os.environ["HF_HOME"] = "/tmp/hf"
-os.environ["TRANSFORMERS_CACHE"] = "/tmp/hf"
-os.environ["XDG_CACHE_HOME"] = "/tmp/hf"
-os.environ["MPLCONFIGDIR"] = "/tmp/matplotlib"
-db_path = "/tmp/chatter_sessions.db"
-openai.api_key = os.getenv("OPENAI_API_KEY")
-client = OpenAI(api_key=openai.api_key)
-
-# === Language codes ===
-LANG_CODES = {
-    "English": "en", "Spanish": "es", "Hindi": "hi", "French": "fr", "German": "de",
-    "Arabic": "ar", "Chinese": "zh", "Portuguese": "pt", "Japanese": "ja", "Korean": "ko"
-}
-CATEGORIES = ["Clarity", "Structure", "Fluency", "Content Relevance", "Tone & Expression", "Average"]
-
-# === SQLModel setup ===
-class SessionEntry(SQLModel, table=True):
-    id: Optional[int] = Field(default=None, primary_key=True)
-    user: str
-    timestamp: str
-    transcript: str
-    feedback: str
-    language: str
-
-engine = create_engine(f"sqlite:///{db_path}")
-SQLModel.metadata.create_all(engine)
-
-def save_to_db(user, transcript, feedback, language):
-    session = Session(engine)
-    entry = SessionEntry(
-        user=user,
-        timestamp=datetime.now().strftime("%Y-%m-%d %H:%M"),
-        transcript=transcript,
-        feedback=feedback,
-        language=language
-    )
-    session.add(entry)
-    session.commit()
-    session.close()
-
-def fetch_user_sessions(user):
-    session = Session(engine)
-    statement = select(SessionEntry).where(SessionEntry.user == user)
-    results = session.exec(statement).all()
-    session.close()
-    return results
-
-# === Whisper ===
-model = WhisperModel("base", compute_type="int8")
-
-def convert_to_wav(input_file):
-    output_wav = f"/tmp/{uuid.uuid4()}.wav"
-    command = ["ffmpeg", "-y", "-i", input_file, "-ar", "16000", "-ac", "1", output_wav]
-    subprocess.run(command, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
-    return output_wav
-
-def transcribe_audio(audio_path):
-    segments, _ = model.transcribe(audio_path)
-    return " ".join([segment.text for segment in segments])
-
-# === GPT-4 Feedback ===
-def generate_feedback(transcript, language):
-    prompt = f"""You are a communication coach. Please respond in [language={language}].
-Evaluate the user's speech on:
-1. Clarity
-2. Structure
-3. Fluency
-4. Content Relevance
-5. Tone & Expression
-Each category:
-- Score out of 10
-- Short explanation
-End with:
-- Overall feedback summary
-- One motivational line
-Transcript:
-{transcript}
-"""
-    response = client.chat.completions.create(
-        model="gpt-4",
-        messages=[
-            {"role": "system", "content": f"You are a supportive communication coach responding in {language}."},
-            {"role": "user", "content": prompt}
-        ],
-        temperature=0.7
-    )
-    return response.choices[0].message.content
-
-def generate_example_response(transcript, language):
-    prompt = f"""You are a communication coach. Rewrite this speech to make it more polished, fluent, and confident.
-Keep the meaning and tone the same, but improve clarity and structure.
-Transcript:
-{transcript}
-"""
-    response = client.chat.completions.create(
-        model="gpt-4",
-        messages=[
-            {"role": "system", "content": f"Reply in {language}. Provide only the improved version of the speech."},
-            {"role": "user", "content": prompt}
-        ]
-    )
-    return response.choices[0].message.content
-
-def parse_scores(feedback):
-    scores = {}
-    for cat in CATEGORIES[:-1]:  # Skip "Average" for now
-        match = re.search(fr"{cat}:\s*(\d+)/10", feedback)
-        scores[cat] = int(match.group(1)) if match else None
-    values = [s for s in scores.values() if s is not None]
-    scores["Average"] = round(sum(values)/len(values), 2) if values else None
-    return scores
-
-def generate_user_chart(user, metric):
-    sessions = fetch_user_sessions(user)
-    if not sessions or metric not in CATEGORIES:
-        return None
-
-    session_ids = list(range(1, len(sessions) + 1))
-    scores = []
-    for s in sessions:
-        parsed = parse_scores(s.feedback)
-        scores.append(parsed.get(metric, 0))
-
-    fig, ax = plt.subplots()
-    ax.plot(session_ids, scores, marker='o', label=metric)
-    ax.set_title(f"{metric} Score Over Time for {user}")
-    ax.set_xlabel("Session")
-    ax.set_ylabel("Score (0–10)")
-    ax.set_ylim(0, 10)
-    ax.grid(True)
-    ax.legend()
-
-    buf = io.BytesIO()
-    plt.savefig(buf, format="png")
-    plt.close(fig)
-    buf.seek(0)
-    return Image.open(buf)
 
-def tutor_feedback(audio_file, language, nickname):
-    if not audio_file or not os.path.exists(audio_file):
-        return "", "No audio received.", None, "", []
-
-    wav_path = convert_to_wav(audio_file)
-    transcript = transcribe_audio(wav_path)
-    feedback_text = generate_feedback(transcript, language)
-
-    lang_code = LANG_CODES.get(language, "en")
-    tts = gTTS(feedback_text, lang=lang_code)
-    mp3_path = f"/tmp/{uuid.uuid4()}.mp3"
-    tts.save(mp3_path)
-
-    save_to_db(nickname, transcript, feedback_text, language)
-    sessions = fetch_user_sessions(nickname)
-
-    return transcript, feedback_text, mp3_path, transcript, [[s.timestamp, s.language, s.transcript[:40], s.feedback[:40]] for s in sessions]
+import gradio as gr
+from spoken_module import spoken_dashboard
 
-# === Gradio Interface ===
 with gr.Blocks(css="light_mode_chatter_owl.css") as app:
-    gr.Markdown("""
-    <div id="header" style="text-align: center;">
-        <img src="file/images/chatter_owl.png" width="120">
-        <h2>🦉 Meet <strong>Chatter the Owl</strong></h2>
-        <p>Enter your name, choose a language, and speak! I’ll help you grow as a communicator.</p>
-    </div>
-    """)
-
-    nickname_box = gr.Textbox(label="👤 Your Nickname", placeholder="Enter your name...")
-    language_dropdown = gr.Dropdown(label="🌍 Select Your Language", choices=list(LANG_CODES.keys()), value="English")
-
-    with gr.Row():
-        audio_input = gr.Audio(type="filepath", label="🎙 Speak or Upload Audio")
-
-    transcript_box = gr.Textbox(label="📖 What You Said", interactive=False)
-    feedback_box = gr.Textbox(label="💡 Chatter’s Feedback", interactive=False)
-    audio_output = gr.Audio(label="🔊 Chatter Speaks", type="filepath")
-    hidden_transcript = gr.Textbox(visible=False)
+    study_type = gr.State("spoken")
 
     with gr.Row():
-        try_again = gr.Button("🔁 Try Again")
-        show_example = gr.Button("🎯 Show Me an Example")
-
-    example_box = gr.Textbox(label="🗣 Suggested Improvement", visible=True, placeholder="Click to generate improved speech...")
-    history_table = gr.Dataframe(headers=["🕒 Timestamp", "🌐 Language", "📝 Transcript (Preview)", "📋 Feedback (Preview)"])
-
-    with gr.Row():
-        chart_metric = gr.Dropdown(label="📈 Choose Metric to Visualize", choices=CATEGORIES, value="Average")
-        view_chart = gr.Button("📊 Show Progress Chart")
-
-    chart_output = gr.Image(label="📉 Your Progress")
-
-    audio_input.change(fn=tutor_feedback,
-                       inputs=[audio_input, language_dropdown, nickname_box],
-                       outputs=[transcript_box, feedback_box, audio_output, hidden_transcript, history_table])
-
-    try_again.click(fn=lambda: ("", "", None, "", "", []),
-                    inputs=None,
-                    outputs=[transcript_box, feedback_box, audio_output, hidden_transcript, example_box, history_table])
-
-    show_example.click(fn=generate_example_response,
-                       inputs=[hidden_transcript, language_dropdown],
-                       outputs=example_box)
-
-    view_chart.click(fn=generate_user_chart,
-                     inputs=[nickname_box, chart_metric],
-                     outputs=chart_output)
+        with gr.Column(scale=1, min_width=200):
+            gr.Markdown("### 📚 Study Modes")
+            btn_spoken = gr.Button("🗣 Spoken Communication")
+            btn_written = gr.Button("✍️ Written Communication")
+            btn_file = gr.Button("📄 File-based Learning")
+
+        with gr.Column(scale=4):
+            output_panel = gr.Column()
+
+            # Dynamic sections
+            spoken_panel = spoken_dashboard()
+            written_panel = gr.Column(visible=False)
+            file_panel = gr.Column(visible=False)
+
+            with written_panel:
+                gr.Markdown("## ✍️ Written Communication (Coming Soon)")
+
+            with file_panel:
+                gr.Markdown("## 📄 File-Based Learning (Coming Soon)")
+
+            def switch_mode(mode):
+                return (
+                    gr.update(visible=(mode == "spoken")),
+                    gr.update(visible=(mode == "written")),
+                    gr.update(visible=(mode == "file")),
+                    mode
+                )
+
+            btn_spoken.click(fn=lambda: switch_mode("spoken"), inputs=[], outputs=[spoken_panel, written_panel, file_panel, study_type])
+            btn_written.click(fn=lambda: switch_mode("written"), inputs=[], outputs=[spoken_panel, written_panel, file_panel, study_type])
+            btn_file.click(fn=lambda: switch_mode("file"), inputs=[], outputs=[spoken_panel, written_panel, file_panel, study_type])
 
-# === Launch ===
 if __name__ == "__main__":
-    print("✅ App is launching...")
-    app.launch(server_name="0.0.0.0", server_port=7860, debug=True)
+    app.launch(server_name="0.0.0.0", server_port=7860)