Update app.py

app.py

@@ -1,13 +1,12 @@
+from PyPDF2 import PdfReader
 from transformers import pipeline, T5ForConditionalGeneration, T5Tokenizer
 import torch
 import gradio as gr
+from gtts import gTTS
 
 # Проверка доступности GPU
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
-# Инициализация модели для распознавания речи (ASR)
-asr_pipeline = pipeline("automatic-speech-recognition", model="openai/whisper-medium", device=0 if device.type == "cuda" else -1)
-
 # Инициализация модели для суммаризации
 summarizer = pipeline("summarization", model="facebook/bart-large-cnn", device=0 if device.type == "cuda" else -1)
 
@@ -16,18 +15,23 @@ model_translation = T5ForConditionalGeneration.from_pretrained('utrobinmv/t5_tra
 model_translation.to(device)
 tokenizer_translation = T5Tokenizer.from_pretrained('utrobinmv/t5_translate_en_ru_zh_small_1024')
 
-def transcribe_audio(audio_file):
-    # Преобразование аудио в текст
-    result = asr_pipeline(audio_file)
-    return result["text"]
+def parse_pdf(pdf_file):
+    """Функция для извлечения текста из PDF файла."""
+    reader = PdfReader(pdf_file)
+    extracted_text = ""
+    for page in reader.pages:
+        extracted_text += page.extract_text() or ""
+    return extracted_text
 
-def summarize(text, max_length=300, min_length=150):
-    # Суммаризация текста
-    result = summarizer(text, max_length=max_length, min_length=min_length, do_sample=False)
+def summarize(text, max_length=1000, min_length=150):
+    """Функция для суммаризации текста."""
+    max_length = 1000  # Можно настроить
+    truncated_text = text[:max_length]
+    result = summarizer(truncated_text, max_length=max_length, min_length=min_length, do_sample=False)
     return result[0]['summary_text']
 
 def translate(text):
-    # Перевод текста на русский
+    """Функция для перевода текста на русский."""
     prefix = 'translate to ru: '
     src_text = prefix + text
 
@@ -37,34 +41,45 @@ def translate(text):
     result = tokenizer_translation.batch_decode(generated_tokens, skip_special_tokens=True)
     return result[0]
 
-def process_audio(audio_file, language):
-    if not audio_file:
+def text_to_speech(text, language='ru'):
+    """Функция для преобразования текста в аудиофайл."""
+    tts = gTTS(text=text, lang=language)
+    audio_file = "output.mp3"
+    tts.save(audio_file)
+    return audio_file
+
+def process_pdf(pdf_file):
+    """Основная функция обработки PDF файла."""
+    if not pdf_file:
         return "No input provided."
-    
-    # Преобразование аудио в текст
-    transcribed_text = transcribe_audio(audio_file)
-    print(f"Transcribed Text: {transcribed_text}")
-    
+
+    # Извлечение текста из PDF
+    extracted_text = parse_pdf(pdf_file)
+    print(f"Extracted Text: {extracted_text}")
+
     # Суммаризация текста
-    summary = summarize(transcribed_text)
+    summary = summarize(extracted_text)
     print(f"Summary: {summary}")
-    
-    # Перевод, если выбран русский язык
-    if language == "rus":
-        return translate(summary)
-    return summary
+
+    # Перевод текста на русский
+    translated_text = translate(summary)
+    print(f"Translated Text: {translated_text}")
+
+    # Преобразование текста в аудио
+    audio_file = text_to_speech(translated_text)
+    return translated_text, audio_file
 
 # Создание Gradio интерфейса
 with gr.Blocks() as demo:
-    gr.Markdown("# Audio Summarizer and Translator")
-    gr.Markdown("Upload an audio file to summarize and translate (if needed).")
+    gr.Markdown("# PDF Summarizer, Translator, and Text-to-Speech")
+    gr.Markdown("Upload a PDF file to summarize, translate to Russian, and convert to audio.")
 
-    language = gr.Radio(choices=["rus", "eng"], label="Output Language", value="rus")
-    audio_input = gr.Audio(label="Upload Audio File", type="filepath")
-    text_output = gr.Textbox(label="Processed Text", lines=10)
-    process_button = gr.Button("Process Audio")
+    pdf_input = gr.File(label="Upload PDF File", type="filepath")
+    text_output = gr.Textbox(label="Translated Text", lines=10)
+    audio_output = gr.Audio(label="Generated Audio", type="filepath")
+    process_button = gr.Button("Process PDF")
 
-    process_button.click(process_audio, inputs=[audio_input, language], outputs=text_output)
+    process_button.click(process_pdf, inputs=pdf_input, outputs=[text_output, audio_output])
 
 # Запуск приложения
 demo.launch(debug=True)