问如何查找加载.txt文件时出现IndexError的原因并解决？Python

EN

    Column 1    Column 2
0   English a   German a
1   English b   German b
2   English c   German c
3   English d   German d
4   ...         ...

# load doc into memory
def load_doc(filename):
# open the file as read only
    file = open(filename, mode='rt', encoding='utf-8')
    # read all text
    text = file.read()
    # close the file
    file.close()
    return text

# split a loaded document into sentences
def to_pairs(doc):
    lines = doc.strip().split('\n')
    pairs = [line.split('\t') for line in lines]  

# clean a list of lines
 def clean_pairs(lines):
    cleaned = list()
    # prepare regex for char filtering
    re_print = re.compile('[^%s]' % re.escape(string.printable))
    # prepare translation table for removing punctuation
    table = str.maketrans('', '', string.punctuation)
    for pair in lines:
        clean_pair = list()
        for line in pair:
            # normalize unicode characters
            line = normalize('NFD', line).encode('ascii', 'ignore')
            line = line.decode('UTF-8')     
            # tokenize on white space
            line = line.split()
            # convert to lowercase
            line = [word.lower() for word in line]       
            # remove punctuation from each token
            line = [word.translate(table) for word in line]       
            # remove non-printable chars form each token
            line = [re_print.sub('', w) for w in line]                 
            # remove tokens with numbers in them
            line = [word for word in line if word.isalpha()]           
            # store as string
            clean_pair.append(' '.join(line))
#            print(clean_pair)
        cleaned.append(clean_pair)
#        print(cleaned)
    print(array(cleaned))
    return array(cleaned) # something goes wrong here

# save a list of clean sentences to file
def save_clean_data(sentences, filename):
    dump(sentences, open(filename, 'wb'))
    print('Saved: %s' % filename)

# load dataset
filename = 'data/dataset.txt'
doc = load_doc(filename)
# split into english-german pairs
pairs = to_pairs(doc)
# clean sentences
clean_pairs = clean_pairs(pairs)
# save clean pairs to file
save_clean_data(clean_pairs, 'english-german.pkl')
# spot check
 for i in range(100):
    print('[%s] => [%s]' % (clean_pairs[i,0], clean_pairs[i,1]))

IndexError                          Traceback (most recent call last)
<ipython-input-2-052d883ebd4c> in <module>()
     72 # spot check
     73 for i in range(100):
---> 74     print('[%s] => [%s]' % (clean_pairs[i,0], clean_pairs[i,1]))
     75 
     76 # load a clean dataset

IndexError: too many indices for array

# Standard dataset:
return array(cleaned)
[['hi' 'hallo']
 ['hi' 'gru gott']
 ['run' ‘lauf’]]

# My own dataset:
return array(cleaned)
[list(['hi' 'hallo'])
 list(['hi' 'gru gott'])
 list(['run' ‘lauf’])]