>>> from transformers import pipeline

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

>>> transcriber("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'}

>>> transcriber = pipeline(model="openai/whisper-large-v2")
>>> 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.'}

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

transcriber = pipeline(model="openai/whisper-large-v2", my_parameter=1)

out = transcriber(...)  # This will use `my_parameter=1`.
out = transcriber(..., my_parameter=2)  # This will override and use `my_parameter=2`.
out = transcriber(...)  # This will go back to using `my_parameter=1`.

transcriber = pipeline(model="openai/whisper-large-v2", device=0)

pip install --upgrade accelerate

transcriber = pipeline(model="openai/whisper-large-v2", device_map="auto")

transcriber = pipeline(model="openai/whisper-large-v2", device=0, batch_size=2)
audio_filenames = [f"https://huggingface.co/datasets/Narsil/asr_dummy/resolve/main/{i}.flac" for i in range(1, 5)]
texts = transcriber(audio_filenames)

>>> transcriber = pipeline(model="openai/whisper-large-v2", return_timestamps=True)
>>> 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.', 'chunks': [{'timestamp': (0.0, 11.88), 'text': ' I have a dream that one day this nation will rise up and live out the true meaning of its'}, {'timestamp': (11.88, 12.38), 'text': ' creed.'}]}

>>> transcriber = pipeline(model="openai/whisper-large-v2", chunk_length_s=30)
>>> transcriber("https://huggingface.co/datasets/reach-vb/random-audios/resolve/main/ted_60.wav")
{'text': " So in college, I was a government major, which means I had to write a lot of papers. Now, when a normal student writes a paper, they might spread the work out a little like this. So, you know. You get started maybe a little slowly, but you get enough done in the first week that with some heavier days later on, everything gets done and things stay civil. And I would want to do that like that. That would be the plan. I would have it all ready to go, but then actually the paper would come along, and then I would kind of do this. And that would happen every single paper. But then came my 90-page senior thesis, a paper you're supposed to spend a year on. I knew for a paper like that, my normal workflow was not an option, it was way too big a project. So I planned things out and I decided I kind of had to go something like this. This is how the year would go. So I'd start off light and I'd bump it up"}

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("This is a cool example!", 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)

pip install gradio

from transformers import pipeline
import gradio as gr

pipe = pipeline("image-classification", model="google/vit-base-patch16-224")

gr.Interface.from_pipeline(pipe).launch()