# Ensure sentence completion at "."

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fensure-sentence-completion-at%2F35179%3E%5C
**Category:** 🤗Transformers\
**Created:** [March 31, 2023, 11:18am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fensure-sentence-completion-at%2F35179 "2023-03-31T11:18:12Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![ffer](https://avatars.discourse-cdn.com/v4/letter/f/f19dbf/32.png) [@ffer](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fffer)%5C
**Post date:** [March 31, 2023, 11:18am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fensure-sentence-completion-at%2F35179%2F1 "2023-03-31T11:18:12Z")

</div>

Hello I’m trying to avoid output truncation during text summarization. I’ve been tuning parameters of the .generate() function such as max\_length, num\_beams, early\_stopping…

I found out I could use StoppingCriteriaList class to specify that I want to stop generation when a dot (.) is generated but apparently this is ignored since I sometimes get an output with two sentences (ending in dot). This is my code so far:

```auto
from transformers import StoppingCriteriaList

def my_stopping_criteria(output):
    if output!=None:
        if "." in output["generated_text"]:
            return True
        
stopping_criteria = StoppingCriteriaList([lambda self, output: my_stopping_criteria(output)])

inputs = tokenizer(texto, return_tensors="pt").input_ids
outputs = model.generate(inputs, max_length = 1000, stopping_criteria=stopping_criteria, num_beams = 3, no_repeat_ngram_size=2, early_stopping=False)
tokenizer.decode(outputs[0],skip_special_tokens=True)

```

In the end I simply want my output not being truncated. Does anyone know how to achieve that while doing text summarization?