# 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/tiZFewofSLM?rel=0&amp;controls=0&amp;showinfo=0" frameborder="0" allowfullscreen></iframe>')

from transformers import pipeline

classifier = pipeline("sentiment-analysis")

classifier("We are very happy to show you the 🤗 Transformers library.")

results = classifier(["We are very happy to show you the 🤗 Transformers library.", "We hope you don't hate it."])
for result in results:
    print(f"label: {result['label']}, with score: {round(result['score'], 4)}")

from transformers import pipeline

speech_recognizer = pipeline("automatic-speech-recognition", model="facebook/wav2vec2-base-960h", device=0)

import datasets

dataset = datasets.load_dataset("superb", name="asr", split="test")

from transformers.pipelines.base import KeyDataset
from tqdm.auto import tqdm

for out in tqdm(speech_recognizer(KeyDataset(dataset, "file"))):
    print(out)

model_name = "nlptown/bert-base-multilingual-uncased-sentiment"

from transformers import AutoTokenizer, AutoModelForSequenceClassification

model = AutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

from transformers import AutoTokenizer, TFAutoModelForSequenceClassification

model = TFAutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

classifier = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)
classifier("Nous sommes très heureux de vous présenter la bibliothèque 🤗 Transformers.")

#@title
from IPython.display import HTML

HTML('<iframe width="560" height="315" src="https://www.youtube.com/embed/AhChOFRegn4?rel=0&amp;controls=0&amp;showinfo=0" frameborder="0" allowfullscreen></iframe>')

from transformers import AutoTokenizer

model_name = "nlptown/bert-base-multilingual-uncased-sentiment"
tokenizer = AutoTokenizer.from_pretrained(model_name)

encoding = tokenizer("We are very happy to show you the 🤗 Transformers library.")
print(encoding)

pt_batch = tokenizer(
    ["We are very happy to show you the 🤗 Transformers library.", "We hope you don't hate it."],
    padding=True,
    truncation=True,
    max_length=512,
    return_tensors="pt",
)

tf_batch = tokenizer(
    ["We are very happy to show you the 🤗 Transformers library.", "We hope you don't hate it."],
    padding=True,
    truncation=True,
    max_length=512,
    return_tensors="tf",
)

from transformers import AutoModelForSequenceClassification

model_name = "nlptown/bert-base-multilingual-uncased-sentiment"
pt_model = AutoModelForSequenceClassification.from_pretrained(model_name)

from transformers import TFAutoModelForSequenceClassification

model_name = "nlptown/bert-base-multilingual-uncased-sentiment"
tf_model = TFAutoModelForSequenceClassification.from_pretrained(model_name)

pt_outputs = pt_model(**pt_batch)

tf_outputs = tf_model(tf_batch)

from torch import nn

pt_predictions = nn.functional.softmax(pt_outputs.logits, dim=-1)
print(pt_predictions)

import tensorflow as tf

tf_predictions = tf.nn.softmax(tf_outputs.logits, axis=-1)
print(tf_predictions)

pt_save_directory = "./pt_save_pretrained"
tokenizer.save_pretrained(pt_save_directory)
pt_model.save_pretrained(pt_save_directory)

tf_save_directory = "./tf_save_pretrained"
tokenizer.save_pretrained(tf_save_directory)
tf_model.save_pretrained(tf_save_directory)

pt_model = AutoModelForSequenceClassification.from_pretrained("./pt_save_pretrained")

tf_model = TFAutoModelForSequenceClassification.from_pretrained("./tf_save_pretrained")

from transformers import AutoModel

tokenizer = AutoTokenizer.from_pretrained(tf_save_directory)
pt_model = AutoModelForSequenceClassification.from_pretrained(tf_save_directory, from_tf=True)

from transformers import TFAutoModel

tokenizer = AutoTokenizer.from_pretrained(pt_save_directory)
tf_model = TFAutoModelForSequenceClassification.from_pretrained(pt_save_directory, from_pt=True)