Upload app.py

app.py

@@ -10,6 +10,7 @@ import soundfile as sf
 import whisper
 import pandas as pd
 from gtts import gTTS
+import re # Necesario para limpiar nombres de archivo
 
 # --- 0. CONFIGURACIÓN INICIAL ---
 try:
@@ -19,12 +20,12 @@ 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") 
 print("Whisper model loaded.")
 
 
 # --- 1. DEFINICIÓN DE PROMPTS PARA LA IA ---
-# (Estos son los prompts completos y correctos para cada función)
 
 CONVERSATION_SYSTEM_PROMPT = """
 You are a friendly and encouraging English language tutor named Alex. 
@@ -122,30 +123,29 @@ def run_sentence_evaluation(audio_input, reference_transcript):
         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'])
-        os.makedirs("reference_audio", exist_ok=True)
+        print("Generando audios de referencia...")
         reference_audio_paths = []
+        os.makedirs("reference_audio", exist_ok=True) 
         for index, row in word_analysis_df.iterrows():
-            word_to_speak = row['reference_word']; audio_path = f"reference_audio/{index}_{word_to_speak.lower()}.mp3"
+            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"
             try:
                 tts = gTTS(text=word_to_speak, lang='en'); tts.save(audio_path); reference_audio_paths.append(audio_path)
-            except Exception: reference_audio_paths.append(None)
+            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, gr.DataFrame(value=df_for_display))
+        return (result.get("overall_score_100", 0), result.get("cefr_level", "N/A"), holistic_feedback_md, df_for_display)
     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
 
 
-# --- 3. INTERFAZ DE GRADIO CON PESTAÑAS (Con la tabla corregida) ---
-
+# --- 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)"):
-            # ... (todo el código de la interfaz del chatbot se mantiene igual)
             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")
@@ -155,12 +155,11 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
             history = gr.State([])
             audio_in_chat.stop_recording(fn=chat_interaction, inputs=[audio_in_chat, history], outputs=[chatbot, history, feedback_en_out, feedback_es_out])
 
-        # --- PESTAÑA 2: EVALUACIÓN POR FRASE (Con la tabla corregida) ---
+        # --- PESTAÑA 2: EVALUACIÓN POR FRASE ---
         with gr.TabItem("Evaluación por Frase"):
             TONGUE_TWISTERS = ["Peter Piper picked a peck of pickled peppers.", "She sells seashells by the seashore.", "How much wood would a woodchuck chuck if a woodchuck could chuck wood?", "Betty Botter bought some butter but she said the butter’s bitter.", "A proper copper coffee pot."]
             gr.Markdown("Choose a tongue twister or write your own sentence. Record yourself, and our AI examiner will provide a detailed diagnostic report.")
             tongue_twister_selector = gr.Dropdown(choices=TONGUE_TWISTERS, label="Or Choose a Tongue Twister to Practice")
-            
             with gr.Row():
                 with gr.Column(scale=1):
                     audio_in_sentence = gr.Audio(sources=["microphone"], type="numpy", label="1. Record Your Voice")
@@ -172,26 +171,11 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
                         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")
-            
             gr.Markdown("--- \n ### Detailed Word-by-Word Analysis")
-            
-            # --- AJUSTE CLAVE: Especificamos el tipo de dato para cada columna ---
-            word_analysis_out_sentence = gr.DataFrame(
-                headers=["Reference Word", "Spoken Word", "Score (0-100)", "Feedback (English)", "Feedback (Español)", "Reference Audio"],
-                # Le decimos a Gradio que la última columna es de tipo 'audio'
-                datatype=["str", "str", "number", "str", "str", "audio"],
-                label="Phonetic Breakdown", 
-                wrap=True
-            )
-
+            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)
             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.")