Upload app.py

app.py

@@ -10,7 +10,7 @@ import soundfile as sf
 import whisper
 import pandas as pd
 from gtts import gTTS
-import re # Necesario para limpiar nombres de archivo
+import re
 
 # --- 0. CONFIGURACIÓN INICIAL ---
 try:
@@ -20,15 +20,14 @@ except TypeError:
     api_key_found = False
 
 print("Loading Whisper for transcription...")
-# Usamos el modelo 'base' que es un buen compromiso entre velocidad y precisión
-whisper_model = whisper.load_model("base", device="cpu") 
+whisper_model = whisper.load_model("base", device="cpu")
 print("Whisper model loaded.")
 
 
 # --- 1. DEFINICIÓN DE PROMPTS PARA LA IA ---
 
 CONVERSATION_SYSTEM_PROMPT = """
-You are a friendly and encouraging English language tutor named Alex. 
+You are a friendly and encouraging English language tutor named Alex.
 A student will speak to you. Your task is to keep a natural, simple conversation going.
 1. Briefly analyze the user's previous response to estimate their CEFR level (A1, A2, B1, etc.).
 2. Formulate a simple, open-ended follow-up question that is appropriate for THAT estimated level.
@@ -108,85 +107,44 @@ def chat_interaction(audio_input, history_state):
         except (json.JSONDecodeError, KeyError) as e:
             print(f"Error parsing final report: {e}"); return chat_display, history_state, gr.Markdown(value="Error generating report.", visible=True), gr.Markdown(visible=False)
 
-# --- CAMBIO: La función de evaluación ahora devuelve Markdown ---
 def run_sentence_evaluation(audio_input, reference_transcript):
     if not api_key_found: raise gr.Error("OpenAI API key not found.")
     if audio_input is None or not reference_transcript:
         return 0, "N/A", "Please provide both an audio file and the reference text.", ""
-
-    sr, y = audio_input
-    temp_audio_path = "temp_audio_sentence.wav"
-    sf.write(temp_audio_path, y, sr)
-    
+    sr, y = audio_input; temp_audio_path = "temp_audio_sentence.wav"; sf.write(temp_audio_path, y, sr)
     word_features = extract_word_level_features(temp_audio_path)
     if not word_features:
-        return 0, "N/A", "Could not process the audio.", None
-
+        return 0, "N/A", "Could not process the audio.", ""
     prompt_data = {"reference_transcript": reference_transcript, "spoken_words": word_features}
-    
     print("Sending detailed data to GPT-4o for sentence analysis...")
-    response = client.chat.completions.create(
-        model="gpt-4o", 
-        response_format={"type": "json_object"},
-        messages=[{"role": "system", "content": SENTENCE_EVALUATION_SYSTEM_PROMPT}, {"role": "user", "content": json.dumps(prompt_data)}]
-    )
-    
+    response = client.chat.completions.create(model="gpt-4o", response_format={"type": "json_object"}, messages=[{"role": "system", "content": SENTENCE_EVALUATION_SYSTEM_PROMPT}, {"role": "user", "content": json.dumps(prompt_data)}])
     try:
         result = json.loads(response.choices[0].message.content)
         holistic_feedback_md = f"### Strengths\n{result['holistic_feedback']['strengths']}\n\n### Areas for Improvement\n{result['holistic_feedback']['areas_for_improvement']}"
         word_analysis_list = result['word_by_word_analysis']
-        
-        # --- NUEVO: Construir una tabla en Markdown ---
-        md_table = "| Reference Word | Spoken Word | Score | Feedback (EN) | Feedback (ES) | Reference Audio |\n"
-        md_table += "| :--- | :--- | :---: | :--- | :--- | :---: |\n"
-        
-        os.makedirs("reference_audio", exist_ok=True) 
-        
+        md_table = "| Reference Word | Spoken Word | Score | Feedback (EN) | Feedback (ES) | Reference Audio |\n| :--- | :--- | :---: | :--- | :--- | :---: |\n"
+        os.makedirs("reference_audio", exist_ok=True)
         for index, item in enumerate(word_analysis_list):
-            word_to_speak = item['reference_word']
-            safe_filename = re.sub(r'\W+', '', word_to_speak.lower())
-            audio_path = f"reference_audio/{index}_{safe_filename}.mp3"
-            
+            word_to_speak = item['reference_word']; safe_filename = re.sub(r'\W+', '', word_to_speak.lower()); audio_path = f"reference_audio/{index}_{safe_filename}.mp3"
             try:
-                tts = gTTS(text=word_to_speak, lang='en')
-                tts.save(audio_path)
-                # Embed the audio using an HTML5 tag within the Markdown table
-                audio_player = f'<audio src="file/{audio_path}" controls></audio>'
+                tts = gTTS(text=word_to_speak, lang='en'); tts.save(audio_path); audio_player = f'<audio src="file/{audio_path}" controls></audio>'
             except Exception as e:
-                print(f"Error al generar TTS para '{word_to_speak}': {e}")
-                audio_player = "Error"
-
-            # Add a row to the Markdown table
-            md_table += (f"| **{item['reference_word']}** "
-                         f"| {item['spoken_word']} "
-                         f"| {item['word_score_100']} "
-                         f"| {item['feedback_en']} "
-                         f"| {item['feedback_es']} "
-                         f"| {audio_player} |\n")
-
-        return (
-            result.get("overall_score_100", 0), 
-            result.get("cefr_level", "N/A"), 
-            holistic_feedback_md,
-            md_table  # Return the Markdown string instead of a DataFrame
-        )
+                print(f"Error al generar TTS para '{word_to_speak}': {e}"); audio_player = "Error"
+            md_table += (f"| **{item['reference_word']}** | {item['spoken_word']} | {item['word_score_100']} | {item['feedback_en']} | {item['feedback_es']} | {audio_player} |\n")
+        return (result.get("overall_score_100", 0), result.get("cefr_level", "N/A"), holistic_feedback_md, md_table)
     except (json.JSONDecodeError, KeyError) as e:
-        print(f"Error processing API response: {e}")
-        error_msg = "The API response was not in the expected format."
+        print(f"Error processing API response: {e}"); error_msg = "The API response was not in the expected format."
         return 0, "Error", error_msg, ""
 
-
-
-# --- 3. INTERFAZ DE GRADIO CON PESTAÑAS (Con salida Markdown) ---
+# --- 3. INTERFAZ DE GRADIO CON PESTAÑAS ---
 with gr.Blocks(theme=gr.themes.Soft()) as demo:
     gr.Markdown("# 🇬🇧 AI English Speaking Practice & Assessment")
-    
     with gr.Tabs():
-        # --- PESTAÑA 1: CHAT AI (sin cambios) ---
+        # --- PESTAÑA 1: CHAT AI ---
         with gr.TabItem("Práctica Conversacional (Chat AI)"):
             with gr.Row():
                 with gr.Column(scale=2):
-                    chatbot = gr.Chatbot(value=[(None, "Hi there! I'm Alex. How are you doing today?")], label="Conversation with your AI Tutor")
+                    chatbot = gr.Chatbot(value=[(None, "Hi there! I'm Alex. How are you doing today?")], label="Conversation with your AI Tutor", height=500)
                     audio_in_chat = gr.Audio(sources=["microphone"], type="numpy", label="Record your response")
                 with gr.Column(scale=1):
                     gr.Markdown("### Final Report"); feedback_en_out = gr.Markdown(label="English Feedback", visible=False); feedback_es_out = gr.Markdown(label="Retroalimentación en Español", visible=False)
@@ -205,7 +163,7 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
                     submit_btn_sentence = gr.Button("Get Assessment", variant="primary")
                 with gr.Column(scale=2):
                     gr.Markdown("### Assessment Summary")
-                    with gr.Row(): 
+                    with gr.Row():
                         score_out_sentence = gr.Number(label="Overall Score (0-100)", interactive=False)
                         level_out_sentence = gr.Textbox(label="Estimated CEFR Level", interactive=False)
                     holistic_feedback_out_sentence = gr.Markdown(label="Examiner's Feedback")
@@ -213,11 +171,8 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
             word_analysis_out_sentence = gr.Markdown(label="Phonetic Breakdown")
             def update_text(choice): return gr.Textbox(value=choice)
             tongue_twister_selector.change(fn=update_text, inputs=tongue_twister_selector, outputs=text_in_sentence)
-            submit_btn_sentence.click(
-                fn=run_sentence_evaluation, 
-                inputs=[audio_in_sentence, text_in_sentence], 
-                outputs=[score_out_sentence, level_out_sentence, holistic_feedback_out_sentence, word_analysis_out_sentence]
-            )
+            submit_btn_sentence.click(fn=run_sentence_evaluation, inputs=[audio_in_sentence, text_in_sentence], outputs=[score_out_sentence, level_out_sentence, holistic_feedback_out_sentence, word_analysis_out_sentence])
+
 if __name__ == "__main__":
-    if not api_key_found: print("\nFATAL: OpenAI API key not found.")
+    if not api_key_found: print("\nFATAL: OpenAI API key not found. Please set the OPENAI_API_KEY environment variable.")
     else: demo.launch(debug=True)