>>> from transformers import pipeline

>>> generator = pipeline(task="automatic-speech-recognition")

>>> generator("https://huggingface.co/datasets/Narsil/asr_dummy/resolve/main/mlk.flac")
{'text': 'I HAVE A DREAM BUT ONE DAY THIS NATION WILL RISE UP LIVE UP THE TRUE MEANING OF ITS TREES'}

>>> generator = pipeline(model="openai/whisper-large")
>>> generator("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.'}

generator(
    [
        "https://huggingface.co/datasets/Narsil/asr_dummy/resolve/main/mlk.flac",
        "https://huggingface.co/datasets/Narsil/asr_dummy/resolve/main/1.flac",
    ]
)

generator = pipeline(model="openai/whisper-large", my_parameter=1)
out = generator(...)  # これは `my_parameter=1` を使用します。
out = generator(..., my_parameter=2)  # これは上書きして `my_parameter=2` を使用します。
out = generator(...)  # これは再び `my_parameter=1` を使用します。

generator = pipeline(model="openai/whisper-large", device=0)

#!pip install accelerate
generator = pipeline(model="openai/whisper-large", device_map="auto")

generator = pipeline(model="openai/whisper-large", device=0, batch_size=2)
audio_filenames = [f"audio_{i}.flac" for i in range(10)]
texts = generator(audio_filenames)

>>> # Not using whisper, as it cannot provide timestamps.
>>> generator = pipeline(model="facebook/wav2vec2-large-960h-lv60-self", return_timestamps="word")
>>> generator("https://huggingface.co/datasets/Narsil/asr_dummy/resolve/main/mlk.flac")
{'text': 'I HAVE A DREAM BUT ONE DAY THIS NATION WILL RISE UP AND LIVE OUT THE TRUE MEANING OF ITS CREED', 'chunks': [{'text': 'I', 'timestamp': (1.22, 1.24)}, {'text': 'HAVE', 'timestamp': (1.42, 1.58)}, {'text': 'A', 'timestamp': (1.66, 1.68)}, {'text': 'DREAM', 'timestamp': (1.76, 2.14)}, {'text': 'BUT', 'timestamp': (3.68, 3.8)}, {'text': 'ONE', 'timestamp': (3.94, 4.06)}, {'text': 'DAY', 'timestamp': (4.16, 4.3)}, {'text': 'THIS', 'timestamp': (6.36, 6.54)}, {'text': 'NATION', 'timestamp': (6.68, 7.1)}, {'text': 'WILL', 'timestamp': (7.32, 7.56)}, {'text': 'RISE', 'timestamp': (7.8, 8.26)}, {'text': 'UP', 'timestamp': (8.38, 8.48)}, {'text': 'AND', 'timestamp': (10.08, 10.18)}, {'text': 'LIVE', 'timestamp': (10.26, 10.48)}, {'text': 'OUT', 'timestamp': (10.58, 10.7)}, {'text': 'THE', 'timestamp': (10.82, 10.9)}, {'text': 'TRUE', 'timestamp': (10.98, 11.18)}, {'text': 'MEANING', 'timestamp': (11.26, 11.58)}, {'text': 'OF', 'timestamp': (11.66, 11.7)}, {'text': 'ITS', 'timestamp': (11.76, 11.88)}, {'text': 'CREED', 'timestamp': (12.0, 12.38)}]}

def data():
    for i in range(1000):
        yield f"My example {i}"


pipe = pipeline(model="openai-community/gpt2", device=0)
generated_characters = 0
for out in pipe(data()):
    generated_characters += len(out[0]["generated_text"])

# KeyDataset is a util that will just output the item we're interested in.
from transformers.pipelines.pt_utils import KeyDataset
from datasets import load_dataset

pipe = pipeline(model="hf-internal-testing/tiny-random-wav2vec2", device=0)
dataset = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation[:10]")

for out in pipe(KeyDataset(dataset, "audio")):
    print(out)

>>> from transformers import pipeline

>>> vision_classifier = pipeline(model="google/vit-base-patch16-224")
>>> preds = vision_classifier(
...     images="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]
>>> preds
[{'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

>>> # This model is a `zero-shot-classification` model.
>>> # It will classify text, except you are free to choose any label you might imagine
>>> classifier = pipeline(model="facebook/bart-large-mnli")
>>> classifier(
...     "I have a problem with my iphone that needs to be resolved asap!!",
...     candidate_labels=["urgent", "not urgent", "phone", "tablet", "computer"],
... )
{'sequence': 'I have a problem with my iphone that needs to be resolved asap!!', 'labels': ['urgent', 'phone', 'computer', 'not urgent', 'tablet'], 'scores': [0.504, 0.479, 0.013, 0.003, 0.002]}

>>> from transformers import pipeline

>>> vqa = pipeline(model="impira/layoutlm-document-qa")
>>> output = vqa(
...     image="https://huggingface.co/spaces/impira/docquery/resolve/2359223c1837a7587402bda0f2643382a6eefeab/invoice.png",
...     question="What is the invoice number?",
... )
>>> output[0]["score"] = round(output[0]["score"], 3)
>>> output
[{'score': 0.425, 'answer': 'us-001', 'start': 16, 'end': 16}]

# pip install accelerate
import torch
from transformers import pipeline

pipe = pipeline(model="facebook/opt-1.3b", torch_dtype=torch.bfloat16, device_map="auto")
output = pipe("これは素晴らしい例です！", do_sample=True, top_p=0.95)

# pip install accelerate bitsandbytes
import torch
from transformers import pipeline

pipe = pipeline(model="facebook/opt-1.3b", device_map="auto", model_kwargs={"load_in_8bit": True})
output = pipe("This is a cool example!", do_sample=True, top_p=0.95)