How to use flair - 10 common examples

def init(tasks_base_path) -> Tuple[TaggedCorpus, TextRegressor, ModelTrainer]:
    corpus = NLPTaskDataFetcher.load_corpus(NLPTask.REGRESSION, tasks_base_path)

    glove_embedding: WordEmbeddings = WordEmbeddings("glove")
    document_embeddings: DocumentRNNEmbeddings = DocumentRNNEmbeddings(
        [glove_embedding], 128, 1, False, 64, False, False
    )

    model = TextRegressor(document_embeddings)

    trainer = ModelTrainer(model, corpus)

    return corpus, model, trainer

def init(tasks_base_path) -> Tuple[TaggedCorpus, TextRegressor, ModelTrainer]:
    corpus = NLPTaskDataFetcher.load_corpus(NLPTask.REGRESSION, tasks_base_path)

    glove_embedding: WordEmbeddings = WordEmbeddings("glove")
    document_embeddings: DocumentRNNEmbeddings = DocumentRNNEmbeddings(
        [glove_embedding], 128, 1, False, 64, False, False
    )

    model = TextRegressor(document_embeddings)

    trainer = ModelTrainer(model, corpus)

    return corpus, model, trainer

def init(tasks_base_path) -> Tuple[TaggedCorpus, TextRegressor, ModelTrainer]:
    corpus = NLPTaskDataFetcher.load_corpus(NLPTask.REGRESSION, tasks_base_path)

    glove_embedding: WordEmbeddings = WordEmbeddings("glove")
    document_embeddings: DocumentRNNEmbeddings = DocumentRNNEmbeddings(
        [glove_embedding], 128, 1, False, 64, False, False
    )

    model = TextRegressor(document_embeddings)

    trainer = ModelTrainer(model, corpus)

    return corpus, model, trainer

assert text == sentence.to_original_text()

    text = ":    nation on"
    sentence = Sentence(text, use_tokenizer=segtok_tokenizer)
    assert text == sentence.to_original_text()

    text = "I love Berlin."
    sentence = Sentence(text)
    assert text == sentence.to_original_text()

    text = 'Schartau sagte dem " Tagesspiegel " vom Freitag , Fischer sei " in einer Weise aufgetreten , die alles andere als überzeugend war " .'
    sentence = Sentence(text)
    assert text == sentence.to_original_text()

    text = 'Schartau sagte dem " Tagesspiegel " vom Freitag , Fischer sei " in einer Weise aufgetreten , die alles andere als überzeugend war " .'
    sentence = Sentence(text, use_tokenizer=segtok_tokenizer)
    assert text == sentence.to_original_text()

# init forward LM with 128 hidden states and 1 layer
    language_model: LanguageModel = LanguageModel(dictionary, is_forward_lm=True, hidden_size=128, nlayers=1)

    # get the example corpus and process at character level in forward direction
    corpus: TextCorpus = TextCorpus(str(Path(__file__).parent / 'resources/corpora/lorem_ipsum'),
                                    dictionary,
                                    language_model.is_forward_lm,
                                    character_level=True)

    # train the language model
    trainer: LanguageModelTrainer = LanguageModelTrainer(language_model, corpus)
    trainer.train('./results', sequence_length=10, mini_batch_size=10, max_epochs=5)

    # use the character LM as embeddings to embed the example sentence 'I love Berlin'
    char_lm_embeddings = CharLMEmbeddings('./results/best-lm.pt')
    sentence = Sentence('I love Berlin')
    char_lm_embeddings.embed(sentence)
    print(sentence[1].embedding.size())

    # clean up results directory
    shutil.rmtree('./results', ignore_errors=True)

def embed_sentence(
        sentence: str,
        pooling_operation,
        layers: str = "1",
        use_scalar_mix: bool = False,
    ) -> Sentence:
        embeddings = CamembertEmbeddings(
            pretrained_model_name_or_path=camembert_model,
            layers=layers,
            pooling_operation=pooling_operation,
            use_scalar_mix=use_scalar_mix,
        )
        flair_sentence = Sentence(sentence)
        embeddings.embed(flair_sentence)

        return flair_sentence

def embed_sentence(
        sentence: str,
        pooling_operation,
        layers: str = "1",
        use_scalar_mix: bool = False,
    ) -> Sentence:
        embeddings = OpenAIGPTEmbeddings(
            pretrained_model_name_or_path=gpt_model,
            layers=layers,
            pooling_operation=pooling_operation,
            use_scalar_mix=use_scalar_mix,
        )
        flair_sentence = Sentence(sentence)
        embeddings.embed(flair_sentence)

        return flair_sentence

def embed_sentence(
        sentence: str,
        pooling_operation,
        layers: str = "1",
        use_scalar_mix: bool = False,
    ) -> Sentence:
        embeddings = RoBERTaEmbeddings(
            pretrained_model_name_or_path=roberta_model,
            layers=layers,
            pooling_operation=pooling_operation,
            use_scalar_mix=use_scalar_mix,
        )
        flair_sentence = Sentence(sentence)
        embeddings.embed(flair_sentence)

        return flair_sentence

def test_sentence_to_real_string(tasks_base_path):
    sentence: Sentence = Sentence("I love Berlin.", use_tokenizer=segtok_tokenizer)
    assert "I love Berlin." == sentence.to_plain_string()

    corpus = flair.datasets.GERMEVAL(base_path=tasks_base_path)

    sentence = corpus.train[0]
    assert (
        'Schartau sagte dem " Tagesspiegel " vom Freitag , Fischer sei " in einer Weise aufgetreten , die alles andere als überzeugend war " .'
        == sentence.to_tokenized_string()
    )
    assert (
        'Schartau sagte dem "Tagesspiegel" vom Freitag, Fischer sei "in einer Weise aufgetreten, die alles andere als überzeugend war".'
        == sentence.to_plain_string()
    )

    sentence = corpus.train[1]
    assert (

def embed_sentence(
        sentence: str,
        pooling_operation,
        layers: str = "1",
        use_scalar_mix: bool = False,
    ) -> Sentence:
        embeddings = OpenAIGPT2Embeddings(
            pretrained_model_name_or_path=gpt_model,
            layers=layers,
            pooling_operation=pooling_operation,
            use_scalar_mix=use_scalar_mix,
        )
        flair_sentence = Sentence(sentence)
        embeddings.embed(flair_sentence)

        return flair_sentence