Upload app.py

app.py

@@ -108,43 +108,81 @@ 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.", None
-    sr, y = audio_input; temp_audio_path = "temp_audio_sentence.wav"; sf.write(temp_audio_path, y, sr)
+        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)
+    
     word_features = extract_word_level_features(temp_audio_path)
     if not word_features:
         return 0, "N/A", "Could not process the audio.", None
+
     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_df = pd.DataFrame(result['word_by_word_analysis'])
-        print("Generando audios de referencia...")
-        reference_audio_paths = []
+        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) 
-        for index, row in word_analysis_df.iterrows():
-            word_to_speak = row['reference_word']; safe_filename = re.sub(r'\W+', '', word_to_speak.lower()); audio_path = f"reference_audio/{index}_{safe_filename}.mp3"
+        
+        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"
+            
             try:
-                tts = gTTS(text=word_to_speak, lang='en'); tts.save(audio_path); reference_audio_paths.append(audio_path)
+                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>'
             except Exception as e:
-                print(f"Error al generar TTS para '{word_to_speak}': {e}"); reference_audio_paths.append(None)
-        word_analysis_df['reference_audio'] = reference_audio_paths
-        df_for_display = word_analysis_df[['reference_word', 'spoken_word', 'word_score_100', 'feedback_en', 'feedback_es', 'reference_audio']]
-        return (result.get("overall_score_100", 0), result.get("cefr_level", "N/A"), holistic_feedback_md, df_for_display)
+                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
+        )
     except (json.JSONDecodeError, KeyError) as e:
-        print(f"Error processing API response: {e}"); error_msg = "The API response was not in the expected format."
-        return 0, "Error", error_msg, None
+        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 ---
+
+# --- 3. INTERFAZ DE GRADIO CON PESTAÑAS (Con salida Markdown) ---
 with gr.Blocks(theme=gr.themes.Soft()) as demo:
     gr.Markdown("# 🇬🇧 AI English Speaking Practice & Assessment")
+    
     with gr.Tabs():
-        # --- PESTAÑA 1: CHAT AI ---
+        # --- PESTAÑA 1: CHAT AI (sin cambios) ---
         with gr.TabItem("Práctica Conversacional (Chat AI)"):
             with gr.Row():
                 with gr.Column(scale=2):
@@ -172,11 +210,14 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
                         level_out_sentence = gr.Textbox(label="Estimated CEFR Level", interactive=False)
                     holistic_feedback_out_sentence = gr.Markdown(label="Examiner's Feedback")
             gr.Markdown("--- \n ### Detailed Word-by-Word Analysis")
-            word_analysis_out_sentence = gr.DataFrame(headers=["Reference Word", "Spoken Word", "Score (0-100)", "Feedback (English)", "Feedback (Español)", "Reference Audio"], datatype=["str", "str", "number", "str", "str", "filepath"], label="Phonetic Breakdown", wrap=True)
+            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.")
     else: demo.launch(debug=True)