Transformers 4.37 中文文档（十二）（1）

>>> from transformers import pipeline
>>> classifier = pipeline(task="audio-classification", model="superb/hubert-base-superb-er")
>>> preds = classifier("https://huggingface.co/datasets/Narsil/asr_dummy/resolve/main/mlk.flac")
>>> preds = [{"score": round(pred["score"], 4), "label": pred["label"]} for pred in preds]
>>> preds
[{'score': 0.4532, 'label': 'hap'},
 {'score': 0.3622, 'label': 'sad'},
 {'score': 0.0943, 'label': 'neu'},
 {'score': 0.0903, 'label': 'ang'}]

>>> from transformers import pipeline
>>> transcriber = pipeline(task="automatic-speech-recognition", model="openai/whisper-small")
>>> transcriber("https://huggingface.co/datasets/Narsil/asr_dummy/resolve/main/mlk.flac")
{'text': ' I have a dream that one day this nation will rise up and live out the true meaning of its creed.'}

>>> from transformers import pipeline
>>> classifier = pipeline(task="image-classification")
>>> preds = classifier(
...     "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"
... )
>>> preds = [{"score": round(pred["score"], 4), "label": pred["label"]} for pred in preds]
>>> print(*preds, sep="\n")
{'score': 0.4335, 'label': 'lynx, catamount'}
{'score': 0.0348, 'label': 'cougar, puma, catamount, mountain lion, painter, panther, Felis concolor'}
{'score': 0.0324, 'label': 'snow leopard, ounce, Panthera uncia'}
{'score': 0.0239, 'label': 'Egyptian cat'}
{'score': 0.0229, 'label': 'tiger cat'}

>>> from transformers import pipeline
>>> detector = pipeline(task="object-detection")
>>> preds = detector(
...     "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"
... )
>>> preds = [{"score": round(pred["score"], 4), "label": pred["label"], "box": pred["box"]} for pred in preds]
>>> preds
[{'score': 0.9865,
  'label': 'cat',
  'box': {'xmin': 178, 'ymin': 154, 'xmax': 882, 'ymax': 598}}]

>>> from transformers import pipeline
>>> segmenter = pipeline(task="image-segmentation")
>>> preds = segmenter(
...     "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"
... )
>>> preds = [{"score": round(pred["score"], 4), "label": pred["label"]} for pred in preds]
>>> print(*preds, sep="\n")
{'score': 0.9879, 'label': 'LABEL_184'}
{'score': 0.9973, 'label': 'snow'}
{'score': 0.9972, 'label': 'cat'}

>>> from transformers import pipeline
>>> depth_estimator = pipeline(task="depth-estimation")
>>> preds = depth_estimator(
...     "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"
... )

>>> from transformers import pipeline
>>> classifier = pipeline(task="sentiment-analysis")
>>> preds = classifier("Hugging Face is the best thing since sliced bread!")
>>> preds = [{"score": round(pred["score"], 4), "label": pred["label"]} for pred in preds]
>>> preds
[{'score': 0.9991, 'label': 'POSITIVE'}]

>>> from transformers import pipeline
>>> classifier = pipeline(task="ner")
>>> preds = classifier("Hugging Face is a French company based in New York City.")
>>> preds = [
...     {
...         "entity": pred["entity"],
...         "score": round(pred["score"], 4),
...         "index": pred["index"],
...         "word": pred["word"],
...         "start": pred["start"],
...         "end": pred["end"],
...     }
...     for pred in preds
... ]
>>> print(*preds, sep="\n")
{'entity': 'I-ORG', 'score': 0.9968, 'index': 1, 'word': 'Hu', 'start': 0, 'end': 2}
{'entity': 'I-ORG', 'score': 0.9293, 'index': 2, 'word': '##gging', 'start': 2, 'end': 7}
{'entity': 'I-ORG', 'score': 0.9763, 'index': 3, 'word': 'Face', 'start': 8, 'end': 12}
{'entity': 'I-MISC', 'score': 0.9983, 'index': 6, 'word': 'French', 'start': 18, 'end': 24}
{'entity': 'I-LOC', 'score': 0.999, 'index': 10, 'word': 'New', 'start': 42, 'end': 45}
{'entity': 'I-LOC', 'score': 0.9987, 'index': 11, 'word': 'York', 'start': 46, 'end': 50}
{'entity': 'I-LOC', 'score': 0.9992, 'index': 12, 'word': 'City', 'start': 51, 'end': 55}

>>> from transformers import pipeline
>>> question_answerer = pipeline(task="question-answering")
>>> preds = question_answerer(
...     question="What is the name of the repository?",
...     context="The name of the repository is huggingface/transformers",
... )
>>> print(
...     f"score: {round(preds['score'], 4)}, start: {preds['start']}, end: {preds['end']}, answer: {preds['answer']}"
... )
score: 0.9327, start: 30, end: 54, answer: huggingface/transformers

>>> from transformers import pipeline
>>> summarizer = pipeline(task="summarization")
>>> summarizer(
...     "In this work, we presented the Transformer, the first sequence transduction model based entirely on attention, replacing the recurrent layers most commonly used in encoder-decoder architectures with multi-headed self-attention. For translation tasks, the Transformer can be trained significantly faster than architectures based on recurrent or convolutional layers. On both WMT 2014 English-to-German and WMT 2014 English-to-French translation tasks, we achieve a new state of the art. In the former task our best model outperforms even all previously reported ensembles."
... )
[{'summary_text': ' The Transformer is the first sequence transduction model based entirely on attention . It replaces the recurrent layers most commonly used in encoder-decoder architectures with multi-headed self-attention . For translation tasks, the Transformer can be trained significantly faster than architectures based on recurrent or convolutional layers .'}]

>>> from transformers import pipeline
>>> text = "translate English to French: Hugging Face is a community-based open-source platform for machine learning."
>>> translator = pipeline(task="translation", model="t5-small")
>>> translator(text)
[{'translation_text': "Hugging Face est une tribune communautaire de l'apprentissage des machines."}]

>>> from transformers import pipeline
>>> prompt = "Hugging Face is a community-based open-source platform for machine learning."
>>> generator = pipeline(task="text-generation")
>>> generator(prompt)  # doctest: +SKIP

>>> text = "Hugging Face is a community-based open-source <mask> for machine learning."
>>> fill_mask = pipeline(task="fill-mask")
>>> preds = fill_mask(text, top_k=1)
>>> preds = [
...     {
...         "score": round(pred["score"], 4),
...         "token": pred["token"],
...         "token_str": pred["token_str"],
...         "sequence": pred["sequence"],
...     }
...     for pred in preds
... ]
>>> preds
[{'score': 0.2236,
  'token': 1761,
  'token_str': ' platform',
  'sequence': 'Hugging Face is a community-based open-source platform for machine learning.'}]

>>> from transformers import pipeline
>>> from PIL import Image
>>> import requests
>>> url = "https://datasets-server.huggingface.co/assets/hf-internal-testing/example-documents/--/hf-internal-testing--example-documents/test/2/image/image.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw)
>>> doc_question_answerer = pipeline("document-question-answering", model="magorshunov/layoutlm-invoices")
>>> preds = doc_question_answerer(
...     question="What is the total amount?",
...     image=image,
... )
>>> preds
[{'score': 0.8531, 'answer': '17,000', 'start': 4, 'end': 4}]