Multiprocessing with loading well-trained model. (via Python3)

[Chris2013]

Here is my situation: I have a well-trained model of speech synthesizing. I am going to speed up synthesizing paces with multiprocessing, which pre-loading the model in each CPU and then keep inputting the sentences for text-to-speech.

Here is my trying-script:

####################################################################
#!/usr/bin/python3
####################################################################

from multiprocessing import Process, Pool, cpu_count
import os,time

####################################################################

from tacotron.demo_synthesizer import Synthesizer
from splitting_sent import splitting_para
import tensorflow as tf
from datasets import audio

####################################################################

from pypinyin import pinyin, Style

####################################################################

BASE_DIR = os.path.split(os.path.realpath(__file__))[0]
VOICE = BASE_DIR + "/tmp"
TXT = BASE_DIR + "/txt"
os.makedirs(VOICE, exist_ok=True)
os.makedirs(TXT, exist_ok=True)

####################################################################

def syn(py):
    synthesizer = Synthesizer()
    synthesizer.load("/path/to/the/model")
    wav_name = time.time()
    wav_path = VOICE + "/" + str(wav_name)
    wav = synthesizer.synthesize(py)
    audio.save_wav(wav, wav_path)

if __name__ =='__main__':

    with open(os.path.join(TXT, "content.txt"), "r") as f:
        lines = f.read().splitlines()
    lines = "".join(lines)

    sentences = splitting_para(lines)
    # splitting paragraph into individual sentences.

    py_list = []
    for sent in sentences:
        py_sent = pinyin(sent, style=Style.TONE3)
        py_sent = " ".join([i[0] for i in py_sent if i[0].isalnum()])
        py_list.append(py_sent)
    # as I am trying the Chinese TTS, it is the inevitable prerequisite step of translating Chinese character into Pinyin.

    print('Run the main process (%s).' % (os.getpid()))
    mainStart = time.time()
    p = Pool(cpu_count())
    for py in py_list:
        p.apply_async(syn,args=(py,))

    print('Waiting for all subprocesses done ...')
    p.close()
    p.join()
    print('All subprocesses done')
    mainEnd = time.time()
    print('All process ran %0.2f seconds.' % (mainEnd-mainStart))

I am stuck on this issue: I could only pre-load 12 models into 12 processes for synthesizing the random sentences. However, it is impossible to carry on inputting the next 12 sentences into the pre-load model. The processes were terminated following by the first set of 12-sentences-TTS were finished. I am totally lost here. :(

I appreciate so much if any suggestion post. :)