pip install datasets

>>> from transformers import AutoTokenizer

>>> tokenizer = AutoTokenizer.from_pretrained("google-bert/bert-base-cased")

>>> encoded_input = tokenizer("Do not meddle in the affairs of wizards, for they are subtle and quick to anger.")
>>> print(encoded_input)
{'input_ids': [101, 2079, 2025, 19960, 10362, 1999, 1996, 3821, 1997, 16657, 1010, 2005, 2027, 2024, 11259, 1998, 4248, 2000, 4963, 1012, 102],
 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]}

>>> tokenizer.decode(encoded_input["input_ids"])
'[CLS] Do not meddle in the affairs of wizards, for they are subtle and quick to anger. [SEP]'

>>> batch_sentences = [
...     "But what about second breakfast?",
...     "Don't think he knows about second breakfast, Pip.",
...     "What about elevensies?",
... ]
>>> encoded_inputs = tokenizer(batch_sentences)
>>> print(encoded_inputs)
{'input_ids': [[101, 1252, 1184, 1164, 1248, 6462, 136, 102],
               [101, 1790, 112, 189, 1341, 1119, 3520, 1164, 1248, 6462, 117, 21902, 1643, 119, 102],
               [101, 1327, 1164, 5450, 23434, 136, 102]],
 'token_type_ids': [[0, 0, 0, 0, 0, 0, 0, 0],
                    [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
                    [0, 0, 0, 0, 0, 0, 0]],
 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1],
                    [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
                    [1, 1, 1, 1, 1, 1, 1]]}

>>> batch_sentences = [
...     "But what about second breakfast?",
...     "Don't think he knows about second breakfast, Pip.",
...     "What about elevensies?",
... ]
>>> encoded_input = tokenizer(batch_sentences, padding=True)
>>> print(encoded_input)
{'input_ids': [[101, 1252, 1184, 1164, 1248, 6462, 136, 102, 0, 0, 0, 0, 0, 0, 0],
               [101, 1790, 112, 189, 1341, 1119, 3520, 1164, 1248, 6462, 117, 21902, 1643, 119, 102],
               [101, 1327, 1164, 5450, 23434, 136, 102, 0, 0, 0, 0, 0, 0, 0, 0]],
 'token_type_ids': [[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
                    [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
                    [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]],
 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0],
                    [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
                    [1, 1, 1, 1, 1, 1, 1, 0، 0، 0، 0، 0، 0، 0، 0]]}

>>> batch_sentences = [
...     "But what about second breakfast?",
...     "Don't think he knows about second breakfast, Pip.",
...     "What about elevensies?",
... ]
>>> encoded_input = tokenizer(batch_sentences, padding=True, truncation=True)
>>> print(encoded_input)
{'input_ids': [[101, 1252, 1184, 1164, 1248, 6462, 136, 102, 0, 0, 0, 0, 0, 0, 0],
               [101, 1790, 112, 189, 1341, 1119, 3520, 1164, 1248, 6462, 117, 21902, 1643, 119, 102],
               [101, 1327, 1164, 5450, 23434, 136, 102, 0, 0, 0, 0, 0, 0, 0, 0]],
 'token_type_ids': [[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
                    [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
                    [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0، 0، 0، 0، 0]]،
 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0، 0، 0، 0],
                    [1, 1, 1, 1, 1, 1, 1، 1، 1، 1، 1، 1، 1، 1، 1، 1],
                    [1، 1، 1، 1، 1، 1، 1، 0، 0، 0، 0، 0، 0، 0، 0، 0]]}

>>> from datasets import load_dataset, Audio

>>> dataset = load_dataset("PolyAI/minds14", name="en-US", split="train")

>>> dataset[0]["audio"]
{'array': array([ 0.        ,  0.00024414, -0.00024414, ..., -0.00024414,
         0.        ,  0.        ], dtype=float32),
 'path': '/root/.cache/huggingface/datasets/downloads/extracted/f14948e0e84be638dd7943ac36518a4cf3324e8b7aa331c5ab11541518e9368c/en-US~JOINT_ACCOUNT/602ba55abb1e6d0fbce92065.wav',
 'sampling_rate': 8000}

>>> dataset = dataset.cast_column("audio", Audio(sampling_rate=16_000))

>>> dataset[0]["audio"]
{'array': array([ 2.3443763e-05,  2.1729663e-04,  2.2145823e-04, ...,
         3.8356509e-05, -7.3497440e-06, -2.1754686e-05], dtype=float32),
 'path': '/root/.cache/huggingface/datasets/downloads/extracted/f14948e0e84be638dd7943ac36518a4cf3324e8b7aa331c5ab11541518e9368c/en-US~JOINT_ACCOUNT/602ba55abb1e6d0fbce92065.wav',
 'sampling_rate': 16000}

>>> from transformers import AutoFeatureExtractor

>>> feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/wav2vec2-base")

>>> audio_input = [dataset[0]["audio"]["array"]]
>>> feature_extractor(audio_input, sampling_rate=16000)
{'input_values': [array([ 3.8106556e-04,  2.7506407e-03,  2.8015103e-03, ...,
        5.6335266e-04,  4.6588284e-06, -1.7142107e-04], dtype=float32)]}

>>> dataset[0]["audio"]["array"].shape
(173398,)

>>> dataset[1]["audio"]["array"].shape
(106496,)

>>> def preprocess_function(examples):
...     audio_arrays = [x["array"] for x in examples["audio"]]
...     inputs = feature_extractor(
...         audio_arrays,
...         sampling_rate=16000,
...         padding=True,
...         max_length=100000,
...         truncation=True,
...     )
...     return inputs

>>> processed_dataset = preprocess_function(dataset[:5])

>>> processed_dataset["input_values"][0].shape
(100000,)

>>> processed_dataset["input_values"][1].shape
(100000,)

>>> from datasets import load_dataset

>>> dataset = load_dataset("food101", split="train[:100]")

>>> dataset[0]["image"]

>>> from transformers import AutoImageProcessor

>>> image_processor = AutoImageProcessor.from_pretrained("google/vit-base-patch16-224")

>>> from torchvision.transforms import RandomResizedCrop, ColorJitter, Compose

>>> size = (
...     image_processor.size["shortest_edge"]
...     if "shortest_edge" in image_processor.size
...     else (image_processor.size["height"], image_processor.size["width"])
... )

>>> _transforms = Compose([RandomResizedCrop(size), ColorJitter(brightness=0.5, hue=0.5)])

>>> def transforms(examples):
...     images = [_transforms(img.convert("RGB")) for img in examples["image"]]
...     examples["pixel_values"] = image_processor(images, do_resize=False, return_tensors="pt")["pixel_values"]
...     return examples

>>> dataset.set_transform(transforms)

>>> dataset[0].keys()

>>> import numpy as np
>>> import matplotlib.pyplot as plt

>>> img = dataset[0]["pixel_values"]
>>> plt.imshow(img.permute(1, 2, 0))

>>> def collate_fn(batch):
...     pixel_values = [item["pixel_values"] for item in batch]
...     encoding = image_processor.pad(pixel_values, return_tensors="pt")
...     labels = [item["labels"] for item in batch]
...     batch = {}
...     batch["pixel_values"] = encoding["pixel_values"]
...     batch["pixel_mask"] = encoding["pixel_mask"]
...     batch["labels"] = labels
...     return batch

>>> from datasets import load_dataset

>>> lj_speech = load_dataset("lj_speech", split="train")

>>> lj_speech = lj_speech.map(remove_columns=["file", "id", "normalized_text"])

>>> lj_speech = lj_speech.map(remove_columns=["file", "id", "normalized_text"])

>>> lj_speech[0]["audio"]
{'array': array([-7.3242188e-04, -7.6293945e-04, -6.4086914e-04, ...,
         7.3242188e-04,  2.1362305e-04,  6.1035156e-05], dtype=float32),
 'path': '/root/.cache/huggingface/datasets/downloads/extracted/917ece08c95cf0c4115e45294e3cd0dee724a1165b7fc11798369308a465bd26/LJSpeech-1.1/wavs/LJ001-0001.wav',
 'sampling_rate': 22050}

>>> lj_speech[0]["text"]
'Printing, in the only sense with which we are at present concerned, differs from most if not from all the arts and crafts represented in the Exhibition'

>>> lj_speech = lj_speech.cast_column("audio", Audio(sampling_rate=16_000))

>>> from transformers import AutoProcessor

>>> processor = AutoProcessor.from_pretrained("facebook/wav2vec2-base-960h")

>>> def prepare_dataset(example):
...     audio = example["audio"]

...     example.update(processor(audio=audio["array"], text=example["text"], sampling_rate=16000))

...     return example

>>> prepare_dataset(lj_speech[0])