# Transformers installation
! pip install transformers datasets
# To install from source instead of the last release, comment the command above and uncomment the following one.
# ! pip install git+https://github.com/huggingface/transformers.git

#@title
from IPython.display import HTML

HTML('<iframe width="560" height="315" src="https://www.youtube.com/embed/Yffk5aydLzg?rel=0&amp;controls=0&amp;showinfo=0" frameborder="0" allowfullscreen></iframe>')

from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("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)

tokenizer.decode(encoded_input["input_ids"])

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)

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)

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)

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, return_tensors="pt")
print(encoded_input)

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, return_tensors="tf")
print(encoded_input)

from datasets import load_dataset, Audio

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

dataset[0]["audio"]

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

dataset[0]["audio"]

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)

dataset[0]["audio"]["array"].shape

dataset[1]["audio"]["array"].shape

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

processed_dataset["input_values"][1].shape

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_and_create_pixel_mask(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[0]["audio"]

lj_speech[0]["text"]

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])