app.py

import os

# Настройка переменной окружения
os.environ['TRANSFORMERS_CACHE'] = '/path/to/writable/directory'

from transformers import pipeline
import speech_recognition as sr
from gtts import gTTS
import os
import io
from google.oauth2.credentials import Credentials
from googleapiclient.discovery import build
from googleapiclient.http import MediaIoBaseDownload

# Инициализация модели и токенизатора
model_name = "cointegrated/rut5-base-multitask"
chatbot = pipeline("text-generation", model=model_name)

# Функция для распознавания речи
def recognize_speech():
    recognizer = sr.Recognizer()
    with sr.Microphone() as source:
        print("Скажите что-нибудь...")
        audio = recognizer.listen(source)
    try:
        text = recognizer.recognize_google(audio, language="ru-RU")
        print("Вы сказали: " + text)
        return text
    except sr.UnknownValueError:
        print("Не удалось распознавать речь")
        return ""
    except sr.RequestError as e:
        print("Ошибка сервиса распознавания речи; {0}".format(e))
        return ""

# Функция для синтезиса речи
def synthesize_speech(text):
    tts = gTTS(text=text, lang="ru")
    tts.save("response.mp3")
    os.system("mpg321 response.mp3")

# Функция для загрузкии документов с Google Drive
def load_documents_from_drive():
    creds = Credentials.from_authorized_user_file('token.json', ['https://www.googleapis.com/auth/drive.readonly'])
    service = build('drive', 'v3', credentials=creds)
    results = service.files().list(q="mimeType='application/pdf' and trashed=false", fields="files(id, name)").execute()
    items = results.get('files', [])
    documents = []
    for item in items:
        file_id = item['id']
        request = service.files().get_media(fileId=file_id)
        fh = io.FileIO(item['name'], 'wb')
        downloader = MediaIoBaseDownload(fh, request)
        done = False
        while done is False:
            status, done = downloader.next_chunk()
            print(f"Скачивание файла {item['name']}... {int(status.progress() * 100)}% завершено")
        fh.close()
        documents.append(item['name'])
    return documents

# Основой цикл чатбота
def main():
    while True:
        user_input = recognize_speech()
        if user_input:
            response = chatbot(user_input, max_length=100, numreturn_sequences=1)[0]['generated_text']
            print("Чатбот: " + response)
            synthesize_speech(response)

if __name__ == "__main__":
    main()