# TypeError: decode() got an unexpected keyword argument 'clean\_up\_tokenization\_spaces'

**URL:** <https://discuss.huggingface.co/t/typeerror-decode-got-an-unexpected-keyword-argument-clean-up-tokenization-spaces/31145>\
**Category:** Beginners\
**Created:** [February 5, 2023, 1:02pm UTC](https://discuss.huggingface.co/t/typeerror-decode-got-an-unexpected-keyword-argument-clean-up-tokenization-spaces/31145 "2023-02-05T13:02:13Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![adib-enc](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/adib-enc/32/13307_2.png) [@adib-enc](https://discuss.huggingface.co/u/adib-enc)\
**Post date:** [February 5, 2023, 1:02pm UTC](https://discuss.huggingface.co/t/typeerror-decode-got-an-unexpected-keyword-argument-clean-up-tokenization-spaces/31145/1 "2023-02-05T13:02:13Z")

</div>

I’m using this code to try indonesian MBART pretrained model. I’m going to use it for summarization.

```python
from transformers import Seq2SeqTrainingArguments, Seq2SeqTrainer, pipeline
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, DataCollatorForSeq2Seq
from indobenchmark import IndoNLGTokenizer
import time
import tensorflow as tf
import os, re, logging
import pandas as pd

model1 = "indobenchmark/indobart-v2"
print(model1)

tokenizer = IndoNLGTokenizer.from_pretrained("indobenchmark/indobart-v2")
model = AutoModelForSeq2SeqLM.from_pretrained(model1)

summarizer = pipeline(
    "summarization", model=model, tokenizer=tokenizer, 
    num_beams=5, do_sample=True, no_repeat_ngram_size=3
)

summarizer(
    "some indonesian article",
    min_length=20,
    max_length=144,
)

```

the code throws this error

```auto
TypeError: decode() got an unexpected keyword argument 'clean_up_tokenization_spaces'

```

complete stacktrace : [err mbart indobenchmark · GitHub](https://gist.github.com/adibenc/29fcbb64305ddff102cc2bebd4b87dd0). Note that this error shows at jupyter notebook.

I always get such an error while inferencing using pipeline. What’s actually going wrong here?

I also using this method to try to generate summary. It runs normally.

```python
def sumt5m(model, pr):
	input_ids = tokenizer.encode(pr, max_length=10240, return_tensors='pt')
	summary_ids = model.generate(input_ids,
				max_length=100, 
				num_beams=2,
				repetition_penalty=2.5, 
				length_penalty=1.0, 
				early_stopping=True,
				no_repeat_ngram_size=2,
				use_cache=True)
	return tokenizer.decode(summary_ids[0], skip_special_tokens=True)

```

---

<div class="post-metadata">

**Author:** ![adib-enc](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/adib-enc/32/13307_2.png) [@adib-enc](https://discuss.huggingface.co/u/adib-enc)\
**Post date:** [February 13, 2023, 9:22am UTC](https://discuss.huggingface.co/t/typeerror-decode-got-an-unexpected-keyword-argument-clean-up-tokenization-spaces/31145/2 "2023-02-13T09:22:23Z")

</div>

Apparently I used custom tokenizer from indobenchmark, and the code is a bit outdated. I fixed it by adding `clean_up_tokenization_spaces` arg to correctly override `decode` method from `PreTrainedTokenizer` baseclass, like this

```auto
	def decode(self, inputs, skip_special_tokens=False, clean_up_tokenization_spaces: bool = True):
		outputs = super().decode(inputs, skip_special_tokens=skip_special_tokens, clean_up_tokenization_spaces=clean_up_tokenization_spaces)
		return outputs.replace(' ','').replace('▁', ' ')

```