How to beginner · 3 min read

How to use text classification pipeline Hugging Face

Q: How to use text classification pipeline Hugging Face

Use the Hugging Face transformers library's pipeline function with the task set to text-classification to classify text. Load a pretrained model like distilbert-base-uncased-finetuned-sst-2-english and pass your text to get classification labels and scores.

Quick answer

Use the Hugging Face transformers library's pipeline function with the task set to text-classification to classify text. Load a pretrained model like distilbert-base-uncased-finetuned-sst-2-english and pass your text to get classification labels and scores.

PREREQUISITES

Python 3.8+
pip install transformers>=4.0.0
pip install torch (or tensorflow)
Internet connection to download pretrained models

Setup

Install the transformers library and a backend like torch or tensorflow. Set up your Python environment with these commands:

bash

pip install transformers torch

Step by step

Use the pipeline API for text classification. This example uses the distilbert-base-uncased-finetuned-sst-2-english model for sentiment analysis:

python

from transformers import pipeline

# Initialize the text classification pipeline
classifier = pipeline('text-classification', model='distilbert-base-uncased-finetuned-sst-2-english')

# Input text to classify
texts = [
    "I love using Hugging Face transformers!",
    "This is the worst movie I have ever seen."
]

# Get classification results
results = classifier(texts)

for text, result in zip(texts, results):
    print(f"Text: {text}\nLabel: {result['label']}, Score: {result['score']:.4f}\n")

output

Text: I love using Hugging Face transformers!
Label: POSITIVE, Score: 0.9998

Text: This is the worst movie I have ever seen.
Label: NEGATIVE, Score: 0.9997

Common variations

Use other pretrained models by changing the model parameter, e.g., roberta-base-finetuned-sentiment.
Run asynchronously with asyncio by wrapping calls in async functions.
Use the pipeline with TensorFlow backend by installing tensorflow instead of torch.

python

from transformers import pipeline

# Using a different model
classifier = pipeline('text-classification', model='roberta-base-finetuned-sentiment')

result = classifier("I am happy with the service.")
print(result)

output

[{'label': 'POSITIVE', 'score': 0.9991}]

Troubleshooting

If you get a ModelNotFoundError, verify the model name is correct and you have internet access to download it.
For slow performance, ensure you have a compatible GPU or use smaller models.
If you see ImportError, confirm transformers and torch are installed properly.

✅

Key Takeaways

Use Hugging Face's pipeline with task text-classification for easy text classification.
Select pretrained models like distilbert-base-uncased-finetuned-sst-2-english for sentiment analysis.
Install transformers and a backend like torch to run the pipeline locally.
You can switch models or run asynchronously for flexibility.
Check model names and dependencies if you encounter errors.

Verified 2026-04 · distilbert-base-uncased-finetuned-sst-2-english, roberta-base-finetuned-sentiment

Verify ↗