desklop / voice_chatbot Goto Github PK

Возинкает ошибка при выборе опции 1:
ValueError: invalid literal for int() with base 10: 'version
что-то с векторами модели.

`python3 bot.py predict

/home/joo/anaconda3/lib/python3.6/site-packages/h5py/init.py:36: FutureWarning: Conversion of the second argument of issubdtype from float to np.floating is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type.
from ._conv import register_converters as _register_converters
Using TensorFlow backend.
/home/joo/anaconda3/lib/python3.6/site-packages/smart_open/ssh.py:34: UserWarning: paramiko missing, opening SSH/SCP/SFTP paths will be disabled. pip install paramiko to suppress
warnings.warn('paramiko missing, opening SSH/SCP/SFTP paths will be disabled. pip install paramiko to suppress')
[i] Выберите набор данных:
1. plays_ru - набор диалогов из пьес
2. conversations_ru - набор диалогов из различных произведений
3. subtitles_ru - набор диалогов из субтитров к 347 сериалам
[W] conversations_ru и subtitles_ru ещё в разработке!
Ваш выбор: 1
[i] Используется набор данных plays_ru
[i] Загрузка параметров модели из data/plays_ru/model_plays_ru.json и data/plays_ru/model_weights_plays_ru.h5
2019-05-12 15:20:13.148420: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2019-05-12 15:20:13.228519: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:964] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2019-05-12 15:20:13.228865: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1432] Found device 0 with properties:
name: GeForce GTX 1080 major: 6 minor: 1 memoryClockRate(GHz): 1.7715
pciBusID: 0000:01:00.0
totalMemory: 7.93GiB freeMemory: 6.86GiB
2019-05-12 15:20:13.228881: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1511] Adding visible gpu devices: 0
2019-05-12 15:20:13.426428: I tensorflow/core/common_runtime/gpu/gpu_device.cc:982] Device interconnect StreamExecutor with strength 1 edge matrix:
2019-05-12 15:20:13.426457: I tensorflow/core/common_runtime/gpu/gpu_device.cc:988] 0
2019-05-12 15:20:13.426463: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1001] 0: N
2019-05-12 15:20:13.426600: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 6609 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1080, pci bus id: 0000:01:00.0, compute capability: 6.1)
[i] Установлена максимальная длина предложения 26 слов(-а)
[i] Загрузка модели word2vec из data/plays_ru/w2v_model_plays_ru.bin...
Traceback (most recent call last):
File "bot.py", line 259, in
main()
File "bot.py", line 202, in main
predict()
File "bot.py", line 143, in predict
ttt = TextToText(f_name_w2v_model=f_name_w2v_model, f_name_model=f_name_model, f_name_model_weights=f_name_model_weights)
File "/home/joo/Документы/LocalRepository/Voice_ChatBot-master/text_to_text.py", line 74, in init
self.w2v = WordToVec(f_name_w2v_model)
File "/home/joo/Документы/LocalRepository/Voice_ChatBot-master/word_to_vec.py", line 33, in init
self.model = word2vec.Word2VecKeyedVectors.load_word2vec_format(f_name_w2v_model, binary=True)
File "/home/joo/anaconda3/lib/python3.6/site-packages/gensim/models/keyedvectors.py", line 1476, in load_word2vec_format
limit=limit, datatype=datatype)
File "/home/joo/anaconda3/lib/python3.6/site-packages/gensim/models/utils_any2vec.py", line 344, in _load_word2vec_format
vocab_size, vector_size = (int(x) for x in header.split()) # throws for invalid file format
File "/home/joo/anaconda3/lib/python3.6/site-packages/gensim/models/utils_any2vec.py", line 344, in
vocab_size, vector_size = (int(x) for x in header.split()) # throws for invalid file format
ValueError: invalid literal for int() with base 10: 'version'`

При выборе опции 3 будет другая ошибка:

File "/home/joo/Документы/LocalRepository/Voice_ChatBot-master/text_to_text.py", line 230, in __load_model with open(f_name_model, 'r') as f_model: FileNotFoundError: [Errno 2] No such file or directory: 'data/subtitles_ru/model_subtitles_ru.json'

1. После запуска docker build -t voice_chatbot:0.1 . выводит

Step 19/41 : RUN unzip install_files/RHVoice.zip
 ---> Running in 673881a195c1
  End-of-central-directory signature not found.  Either this file is not
  a zipfile, or it constitutes one disk of a multi-part archive.  In the
  latter case the central directory and zipfile comment will be found on
  the last disk(s) of this archive.
note:  install_files/RHVoice.zip may be a plain executable, not an archive
unzip:  cannot find zipfile directory in one of install_files/RHVoice.zip or
        install_files/RHVoice.zip.zip, and cannot find install_files/RHVoice.zip.ZIP, period.

2. Если закомментировать Установка RHVoice, билдится успешно, но при запуске контейнера пишет

➜  Voice_ChatBot git:(master) ✗ docker run -ti --rm -p 5000:5000 voice_chatbot:0.1
Traceback (most recent call last):
  File "rest_server.py", line 30, in <module>
    from tensorflow import get_default_graph
ImportError: cannot import name 'get_default_graph'

root@Dell:/home/lavrenkov/Voice_ChatBOt# python3 bot.py train
Traceback (most recent call last):
File "bot.py", line 8, in
from preprocessing import Preparation
File "/home/lavrenkov/Voice_ChatBOt/preprocessing.py", line 11, in
import matplotlib.pyplot as plt
File "/usr/local/lib/python3.6/dist-packages/matplotlib/pyplot.py", line 2374, in
switch_backend(rcParams["backend"])
File "/usr/local/lib/python3.6/dist-packages/matplotlib/pyplot.py", line 207, in switch_backend
backend_mod = importlib.import_module(backend_name)
File "/usr/lib/python3.6/importlib/init.py", line 126, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File "/usr/local/lib/python3.6/dist-packages/matplotlib/backends/backend_tkagg.py", line 1, in
from . import _backend_tk
File "/usr/local/lib/python3.6/dist-packages/matplotlib/backends/_backend_tk.py", line 5, in
import tkinter as Tk
ModuleNotFoundError: No module named 'tkinter'

При попытке использования вылазит ошибка, в чем косяк всё стоит верно!

python3 speech_to_text.py
[i] Загрузка языковой модели... Traceback (most recent call last):
File "speech_to_text.py", line 101, in
main()
File "speech_to_text.py", line 94, in main
sr = SpeechRecognitionclass('from_microphone')
File "speech_to_text.py", line 45, in init
dic=os.path.join(model_path, 'ru_bot.dic')
File "/usr/local/lib/python3.6/dist-packages/pocketsphinx/init.py", line 208, in init
super(LiveSpeech, self).init(**kwargs)
File "/usr/local/lib/python3.6/dist-packages/pocketsphinx/init.py", line 90, in init
super(Pocketsphinx, self).init(config)
File "/usr/local/lib/python3.6/dist-packages/pocketsphinx/pocketsphinx.py", line 275, in init
this = _pocketsphinx.new_Decoder(*args)
RuntimeError: new_Decoder returned -1

root@Dell:/home/lavrenkov/Voice_ChatBOt# python3 preprocessing.py
Ты бот?

root@Dell:/home/lavrenkov/Voice_ChatBOt#

[i] Выберите вариант работы бота:
1. train - обучение модели seq2seq
2. predict - работа с обученной моделью seq2seq
3. predict -ss - включено озвучивание ответов с помощью RHVoice
4. predict -sr - включено распознавание речи с помощью PocketSphinx
5. predict -ss -sr - включено озвучивание ответов и распознавание речи
Введите цифру: 4
[i] Загрузка параметров сети из data/net_model.txt и data/net_final_weights.h5
2018-11-21 19:01:24.488971: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
[i] Инициализация языковой модели...
Traceback (most recent call last):
File "bot.py", line 239, in
main()
File "bot.py", line 218, in main
predict(True, False)
File "bot.py", line 136, in predict
sr = SpeechRecognition('from_microphone')
File "/home/lavrenkov/Voice_ChatBot/speech_to_text.py", line 45, in init
dic=os.path.join(model_path, 'ru_bot.dic')
File "/usr/local/lib/python3.6/dist-packages/pocketsphinx/init.py", line 208, in init
super(LiveSpeech, self).init(**kwargs)
File "/usr/local/lib/python3.6/dist-packages/pocketsphinx/init.py", line 90, in init
super(Pocketsphinx, self).init(config)
File "/usr/local/lib/python3.6/dist-packages/pocketsphinx/pocketsphinx.py", line 273, in init
this = _pocketsphinx.new_Decoder(*args)
RuntimeError: new_Decoder returned -1

Ссылка на файл Install_CUDA10.0_cuDNN_for410.zip не валидна.

Нужно положить акустическую модель в /usr/local/lib/python3.5/dist-packages/pocketsphinx/model. Подробнее про это можно найти в статье на хабре https://habr.com/post/351376/

P.S. Это ошибка не RHVoice, а PocketSphinx.

Просто положить файлы в такую же деректорию для python 3.6 не канает