Transformers
  • 🌍GET STARTED
    • Transformers
    • Quick tour
    • Installation
  • 🌍TUTORIALS
    • Run inference with pipelines
    • Write portable code with AutoClass
    • Preprocess data
    • Fine-tune a pretrained model
    • Train with a script
    • Set up distributed training with BOINC AI Accelerate
    • Load and train adapters with BOINC AI PEFT
    • Share your model
    • Agents
    • Generation with LLMs
  • 🌍TASK GUIDES
    • 🌍NATURAL LANGUAGE PROCESSING
      • Text classification
      • Token classification
      • Question answering
      • Causal language modeling
      • Masked language modeling
      • Translation
      • Summarization
      • Multiple choice
    • 🌍AUDIO
      • Audio classification
      • Automatic speech recognition
    • 🌍COMPUTER VISION
      • Image classification
      • Semantic segmentation
      • Video classification
      • Object detection
      • Zero-shot object detection
      • Zero-shot image classification
      • Depth estimation
    • 🌍MULTIMODAL
      • Image captioning
      • Document Question Answering
      • Visual Question Answering
      • Text to speech
    • 🌍GENERATION
      • Customize the generation strategy
    • 🌍PROMPTING
      • Image tasks with IDEFICS
  • 🌍DEVELOPER GUIDES
    • Use fast tokenizers from BOINC AI Tokenizers
    • Run inference with multilingual models
    • Use model-specific APIs
    • Share a custom model
    • Templates for chat models
    • Run training on Amazon SageMaker
    • Export to ONNX
    • Export to TFLite
    • Export to TorchScript
    • Benchmarks
    • Notebooks with examples
    • Community resources
    • Custom Tools and Prompts
    • Troubleshoot
  • 🌍PERFORMANCE AND SCALABILITY
    • Overview
    • 🌍EFFICIENT TRAINING TECHNIQUES
      • Methods and tools for efficient training on a single GPU
      • Multiple GPUs and parallelism
      • Efficient training on CPU
      • Distributed CPU training
      • Training on TPUs
      • Training on TPU with TensorFlow
      • Training on Specialized Hardware
      • Custom hardware for training
      • Hyperparameter Search using Trainer API
    • 🌍OPTIMIZING INFERENCE
      • Inference on CPU
      • Inference on one GPU
      • Inference on many GPUs
      • Inference on Specialized Hardware
    • Instantiating a big model
    • Troubleshooting
    • XLA Integration for TensorFlow Models
    • Optimize inference using `torch.compile()`
  • 🌍CONTRIBUTE
    • How to contribute to transformers?
    • How to add a model to BOINC AI Transformers?
    • How to convert a BOINC AI Transformers model to TensorFlow?
    • How to add a pipeline to BOINC AI Transformers?
    • Testing
    • Checks on a Pull Request
  • 🌍CONCEPTUAL GUIDES
    • Philosophy
    • Glossary
    • What BOINC AI Transformers can do
    • How BOINC AI Transformers solve tasks
    • The Transformer model family
    • Summary of the tokenizers
    • Attention mechanisms
    • Padding and truncation
    • BERTology
    • Perplexity of fixed-length models
    • Pipelines for webserver inference
    • Model training anatomy
  • 🌍API
    • 🌍MAIN CLASSES
      • Agents and Tools
      • 🌍Auto Classes
        • Extending the Auto Classes
        • AutoConfig
        • AutoTokenizer
        • AutoFeatureExtractor
        • AutoImageProcessor
        • AutoProcessor
        • Generic model classes
          • AutoModel
          • TFAutoModel
          • FlaxAutoModel
        • Generic pretraining classes
          • AutoModelForPreTraining
          • TFAutoModelForPreTraining
          • FlaxAutoModelForPreTraining
        • Natural Language Processing
          • AutoModelForCausalLM
          • TFAutoModelForCausalLM
          • FlaxAutoModelForCausalLM
          • AutoModelForMaskedLM
          • TFAutoModelForMaskedLM
          • FlaxAutoModelForMaskedLM
          • AutoModelForMaskGenerationge
          • TFAutoModelForMaskGeneration
          • AutoModelForSeq2SeqLM
          • TFAutoModelForSeq2SeqLM
          • FlaxAutoModelForSeq2SeqLM
          • AutoModelForSequenceClassification
          • TFAutoModelForSequenceClassification
          • FlaxAutoModelForSequenceClassification
          • AutoModelForMultipleChoice
          • TFAutoModelForMultipleChoice
          • FlaxAutoModelForMultipleChoice
          • AutoModelForNextSentencePrediction
          • TFAutoModelForNextSentencePrediction
          • FlaxAutoModelForNextSentencePrediction
          • AutoModelForTokenClassification
          • TFAutoModelForTokenClassification
          • FlaxAutoModelForTokenClassification
          • AutoModelForQuestionAnswering
          • TFAutoModelForQuestionAnswering
          • FlaxAutoModelForQuestionAnswering
          • AutoModelForTextEncoding
          • TFAutoModelForTextEncoding
        • Computer vision
          • AutoModelForDepthEstimation
          • AutoModelForImageClassification
          • TFAutoModelForImageClassification
          • FlaxAutoModelForImageClassification
          • AutoModelForVideoClassification
          • AutoModelForMaskedImageModeling
          • TFAutoModelForMaskedImageModeling
          • AutoModelForObjectDetection
          • AutoModelForImageSegmentation
          • AutoModelForImageToImage
          • AutoModelForSemanticSegmentation
          • TFAutoModelForSemanticSegmentation
          • AutoModelForInstanceSegmentation
          • AutoModelForUniversalSegmentation
          • AutoModelForZeroShotImageClassification
          • TFAutoModelForZeroShotImageClassification
          • AutoModelForZeroShotObjectDetection
        • Audio
          • AutoModelForAudioClassification
          • AutoModelForAudioFrameClassification
          • TFAutoModelForAudioFrameClassification
          • AutoModelForCTC
          • AutoModelForSpeechSeq2Seq
          • TFAutoModelForSpeechSeq2Seq
          • FlaxAutoModelForSpeechSeq2Seq
          • AutoModelForAudioXVector
          • AutoModelForTextToSpectrogram
          • AutoModelForTextToWaveform
        • Multimodal
          • AutoModelForTableQuestionAnswering
          • TFAutoModelForTableQuestionAnswering
          • AutoModelForDocumentQuestionAnswering
          • TFAutoModelForDocumentQuestionAnswering
          • AutoModelForVisualQuestionAnswering
          • AutoModelForVision2Seq
          • TFAutoModelForVision2Seq
          • FlaxAutoModelForVision2Seq
      • Callbacks
      • Configuration
      • Data Collator
      • Keras callbacks
      • Logging
      • Models
      • Text Generation
      • ONNX
      • Optimization
      • Model outputs
      • Pipelines
      • Processors
      • Quantization
      • Tokenizer
      • Trainer
      • DeepSpeed Integration
      • Feature Extractor
      • Image Processor
    • 🌍MODELS
      • 🌍TEXT MODELS
        • ALBERT
        • BART
        • BARThez
        • BARTpho
        • BERT
        • BertGeneration
        • BertJapanese
        • Bertweet
        • BigBird
        • BigBirdPegasus
        • BioGpt
        • Blenderbot
        • Blenderbot Small
        • BLOOM
        • BORT
        • ByT5
        • CamemBERT
        • CANINE
        • CodeGen
        • CodeLlama
        • ConvBERT
        • CPM
        • CPMANT
        • CTRL
        • DeBERTa
        • DeBERTa-v2
        • DialoGPT
        • DistilBERT
        • DPR
        • ELECTRA
        • Encoder Decoder Models
        • ERNIE
        • ErnieM
        • ESM
        • Falcon
        • FLAN-T5
        • FLAN-UL2
        • FlauBERT
        • FNet
        • FSMT
        • Funnel Transformer
        • GPT
        • GPT Neo
        • GPT NeoX
        • GPT NeoX Japanese
        • GPT-J
        • GPT2
        • GPTBigCode
        • GPTSAN Japanese
        • GPTSw3
        • HerBERT
        • I-BERT
        • Jukebox
        • LED
        • LLaMA
        • LLama2
        • Longformer
        • LongT5
        • LUKE
        • M2M100
        • MarianMT
        • MarkupLM
        • MBart and MBart-50
        • MEGA
        • MegatronBERT
        • MegatronGPT2
        • Mistral
        • mLUKE
        • MobileBERT
        • MPNet
        • MPT
        • MRA
        • MT5
        • MVP
        • NEZHA
        • NLLB
        • NLLB-MoE
        • Nyströmformer
        • Open-Llama
        • OPT
        • Pegasus
        • PEGASUS-X
        • Persimmon
        • PhoBERT
        • PLBart
        • ProphetNet
        • QDQBert
        • RAG
        • REALM
        • Reformer
        • RemBERT
        • RetriBERT
        • RoBERTa
        • RoBERTa-PreLayerNorm
        • RoCBert
        • RoFormer
        • RWKV
        • Splinter
        • SqueezeBERT
        • SwitchTransformers
        • T5
        • T5v1.1
        • TAPEX
        • Transformer XL
        • UL2
        • UMT5
        • X-MOD
        • XGLM
        • XLM
        • XLM-ProphetNet
        • XLM-RoBERTa
        • XLM-RoBERTa-XL
        • XLM-V
        • XLNet
        • YOSO
      • 🌍VISION MODELS
        • BEiT
        • BiT
        • Conditional DETR
        • ConvNeXT
        • ConvNeXTV2
        • CvT
        • Deformable DETR
        • DeiT
        • DETA
        • DETR
        • DiNAT
        • DINO V2
        • DiT
        • DPT
        • EfficientFormer
        • EfficientNet
        • FocalNet
        • GLPN
        • ImageGPT
        • LeViT
        • Mask2Former
        • MaskFormer
        • MobileNetV1
        • MobileNetV2
        • MobileViT
        • MobileViTV2
        • NAT
        • PoolFormer
        • Pyramid Vision Transformer (PVT)
        • RegNet
        • ResNet
        • SegFormer
        • SwiftFormer
        • Swin Transformer
        • Swin Transformer V2
        • Swin2SR
        • Table Transformer
        • TimeSformer
        • UperNet
        • VAN
        • VideoMAE
        • Vision Transformer (ViT)
        • ViT Hybrid
        • ViTDet
        • ViTMAE
        • ViTMatte
        • ViTMSN
        • ViViT
        • YOLOS
      • 🌍AUDIO MODELS
        • Audio Spectrogram Transformer
        • Bark
        • CLAP
        • EnCodec
        • Hubert
        • MCTCT
        • MMS
        • MusicGen
        • Pop2Piano
        • SEW
        • SEW-D
        • Speech2Text
        • Speech2Text2
        • SpeechT5
        • UniSpeech
        • UniSpeech-SAT
        • VITS
        • Wav2Vec2
        • Wav2Vec2-Conformer
        • Wav2Vec2Phoneme
        • WavLM
        • Whisper
        • XLS-R
        • XLSR-Wav2Vec2
      • 🌍MULTIMODAL MODELS
        • ALIGN
        • AltCLIP
        • BLIP
        • BLIP-2
        • BridgeTower
        • BROS
        • Chinese-CLIP
        • CLIP
        • CLIPSeg
        • Data2Vec
        • DePlot
        • Donut
        • FLAVA
        • GIT
        • GroupViT
        • IDEFICS
        • InstructBLIP
        • LayoutLM
        • LayoutLMV2
        • LayoutLMV3
        • LayoutXLM
        • LiLT
        • LXMERT
        • MatCha
        • MGP-STR
        • Nougat
        • OneFormer
        • OWL-ViT
        • Perceiver
        • Pix2Struct
        • Segment Anything
        • Speech Encoder Decoder Models
        • TAPAS
        • TrOCR
        • TVLT
        • ViLT
        • Vision Encoder Decoder Models
        • Vision Text Dual Encoder
        • VisualBERT
        • X-CLIP
      • 🌍REINFORCEMENT LEARNING MODELS
        • Decision Transformer
        • Trajectory Transformer
      • 🌍TIME SERIES MODELS
        • Autoformer
        • Informer
        • Time Series Transformer
      • 🌍GRAPH MODELS
        • Graphormer
  • 🌍INTERNAL HELPERS
    • Custom Layers and Utilities
    • Utilities for pipelines
    • Utilities for Tokenizers
    • Utilities for Trainer
    • Utilities for Generation
    • Utilities for Image Processors
    • Utilities for Audio processing
    • General Utilities
    • Utilities for Time Series
Powered by GitBook
On this page
  • Load OPUS Books dataset
  • Preprocess
  • Evaluate
  • Train
  • Inference
  1. TASK GUIDES
  2. NATURAL LANGUAGE PROCESSING

Translation

Translation converts a sequence of text from one language to another. It is one of several tasks you can formulate as a sequence-to-sequence problem, a powerful framework for returning some output from an input, like translation or summarization. Translation systems are commonly used for translation between different language texts, but it can also be used for speech or some combination in between like text-to-speech or speech-to-text.

This guide will show you how to:

  1. Finetune T5 on the English-French subset of the OPUS Books dataset to translate English text to French.

  2. Use your finetuned model for inference.

The task illustrated in this tutorial is supported by the following model architectures:

BART, BigBird-Pegasus, Blenderbot, BlenderbotSmall, Encoder decoder, FairSeq Machine-Translation, GPTSAN-japanese, LED, LongT5, M2M100, Marian, mBART, MT5, MVP, NLLB, NLLB-MOE, Pegasus, PEGASUS-X, PLBart, ProphetNet, SwitchTransformers, T5, UMT5, XLM-ProphetNet

Before you begin, make sure you have all the necessary libraries installed:

Copied

pip install transformers datasets evaluate sacrebleu

We encourage you to login to your BOINC AI account so you can upload and share your model with the community. When prompted, enter your token to login:

Copied

>>> from boincai_hub import notebook_login

>>> notebook_login()

Load OPUS Books dataset

Start by loading the English-French subset of the OPUS Books dataset from the 🌍 Datasets library:

Copied

>>> from datasets import load_dataset

>>> books = load_dataset("opus_books", "en-fr")

Split the dataset into a train and test set with the train_test_split method:

Copied

>>> books = books["train"].train_test_split(test_size=0.2)

Then take a look at an example:

Copied

>>> books["train"][0]
{'id': '90560',
 'translation': {'en': 'But this lofty plateau measured only a few fathoms, and soon we reentered Our Element.',
  'fr': 'Mais ce plateau élevé ne mesurait que quelques toises, et bientôt nous fûmes rentrés dans notre élément.'}}

translation: an English and French translation of the text.

Preprocess

The next step is to load a T5 tokenizer to process the English-French language pairs:

Copied

>>> from transformers import AutoTokenizer

>>> checkpoint = "t5-small"
>>> tokenizer = AutoTokenizer.from_pretrained(checkpoint)

The preprocessing function you want to create needs to:

  1. Prefix the input with a prompt so T5 knows this is a translation task. Some models capable of multiple NLP tasks require prompting for specific tasks.

  2. Tokenize the input (English) and target (French) separately because you can’t tokenize French text with a tokenizer pretrained on an English vocabulary.

  3. Truncate sequences to be no longer than the maximum length set by the max_length parameter.

Copied

>>> source_lang = "en"
>>> target_lang = "fr"
>>> prefix = "translate English to French: "


>>> def preprocess_function(examples):
...     inputs = [prefix + example[source_lang] for example in examples["translation"]]
...     targets = [example[target_lang] for example in examples["translation"]]
...     model_inputs = tokenizer(inputs, text_target=targets, max_length=128, truncation=True)
...     return model_inputs

To apply the preprocessing function over the entire dataset, use 🌍Datasets map method. You can speed up the map function by setting batched=True to process multiple elements of the dataset at once:

Copied

>>> tokenized_books = books.map(preprocess_function, batched=True)

Now create a batch of examples using DataCollatorForSeq2Seq. It’s more efficient to dynamically pad the sentences to the longest length in a batch during collation, instead of padding the whole dataset to the maximum length.

PytorchHide Pytorch contentCopied

>>> from transformers import DataCollatorForSeq2Seq

>>> data_collator = DataCollatorForSeq2Seq(tokenizer=tokenizer, model=checkpoint)

TensorFlowHide TensorFlow contentCopied

>>> from transformers import DataCollatorForSeq2Seq

>>> data_collator = DataCollatorForSeq2Seq(tokenizer=tokenizer, model=checkpoint, return_tensors="tf")

Evaluate

Including a metric during training is often helpful for evaluating your model’s performance. You can quickly load a evaluation method with the 🌍 Evaluate library. For this task, load the SacreBLEU metric (see the 🌍 Evaluate quick tour to learn more about how to load and compute a metric):

Copied

>>> import evaluate

>>> metric = evaluate.load("sacrebleu")

Then create a function that passes your predictions and labels to compute to calculate the SacreBLEU score:

Copied

>>> import numpy as np


>>> def postprocess_text(preds, labels):
...     preds = [pred.strip() for pred in preds]
...     labels = [[label.strip()] for label in labels]

...     return preds, labels


>>> def compute_metrics(eval_preds):
...     preds, labels = eval_preds
...     if isinstance(preds, tuple):
...         preds = preds[0]
...     decoded_preds = tokenizer.batch_decode(preds, skip_special_tokens=True)

...     labels = np.where(labels != -100, labels, tokenizer.pad_token_id)
...     decoded_labels = tokenizer.batch_decode(labels, skip_special_tokens=True)

...     decoded_preds, decoded_labels = postprocess_text(decoded_preds, decoded_labels)

...     result = metric.compute(predictions=decoded_preds, references=decoded_labels)
...     result = {"bleu": result["score"]}

...     prediction_lens = [np.count_nonzero(pred != tokenizer.pad_token_id) for pred in preds]
...     result["gen_len"] = np.mean(prediction_lens)
...     result = {k: round(v, 4) for k, v in result.items()}
...     return result

Your compute_metrics function is ready to go now, and you’ll return to it when you setup your training.

Train

PytorchHide Pytorch content

If you aren’t familiar with finetuning a model with the Trainer, take a look at the basic tutorial here!

You’re ready to start training your model now! Load T5 with AutoModelForSeq2SeqLM:

Copied

>>> from transformers import AutoModelForSeq2SeqLM, Seq2SeqTrainingArguments, Seq2SeqTrainer

>>> model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint)

At this point, only three steps remain:

  1. Define your training hyperparameters in Seq2SeqTrainingArguments. The only required parameter is output_dir which specifies where to save your model. You’ll push this model to the Hub by setting push_to_hub=True (you need to be signed in to BOINC AI to upload your model). At the end of each epoch, the Trainer will evaluate the SacreBLEU metric and save the training checkpoint.

  2. Pass the training arguments to Seq2SeqTrainer along with the model, dataset, tokenizer, data collator, and compute_metrics function.

  3. Call train() to finetune your model.

Copied

>>> training_args = Seq2SeqTrainingArguments(
...     output_dir="my_awesome_opus_books_model",
...     evaluation_strategy="epoch",
...     learning_rate=2e-5,
...     per_device_train_batch_size=16,
...     per_device_eval_batch_size=16,
...     weight_decay=0.01,
...     save_total_limit=3,
...     num_train_epochs=2,
...     predict_with_generate=True,
...     fp16=True,
...     push_to_hub=True,
... )

>>> trainer = Seq2SeqTrainer(
...     model=model,
...     args=training_args,
...     train_dataset=tokenized_books["train"],
...     eval_dataset=tokenized_books["test"],
...     tokenizer=tokenizer,
...     data_collator=data_collator,
...     compute_metrics=compute_metrics,
... )

>>> trainer.train()

Once training is completed, share your model to the Hub with the push_to_hub() method so everyone can use your model:

Copied

>>> trainer.push_to_hub()

TensorFlowHide TensorFlow content

If you aren’t familiar with finetuning a model with Keras, take a look at the basic tutorial here!

To finetune a model in TensorFlow, start by setting up an optimizer function, learning rate schedule, and some training hyperparameters:Copied

>>> from transformers import AdamWeightDecay

>>> optimizer = AdamWeightDecay(learning_rate=2e-5, weight_decay_rate=0.01)

Then you can load T5 with TFAutoModelForSeq2SeqLM:

Copied

>>> from transformers import TFAutoModelForSeq2SeqLM

>>> model = TFAutoModelForSeq2SeqLM.from_pretrained(checkpoint)

Convert your datasets to the tf.data.Dataset format with prepare_tf_dataset():

Copied

>>> tf_train_set = model.prepare_tf_dataset(
...     tokenized_books["train"],
...     shuffle=True,
...     batch_size=16,
...     collate_fn=data_collator,
... )

>>> tf_test_set = model.prepare_tf_dataset(
...     tokenized_books["test"],
...     shuffle=False,
...     batch_size=16,
...     collate_fn=data_collator,
... )

Configure the model for training with compile. Note that Transformers models all have a default task-relevant loss function, so you don’t need to specify one unless you want to:

Copied

>>> import tensorflow as tf

>>> model.compile(optimizer=optimizer)  # No loss argument!

The last two things to setup before you start training is to compute the SacreBLEU metric from the predictions, and provide a way to push your model to the Hub. Both are done by using Keras callbacks.

Pass your compute_metrics function to KerasMetricCallback:

Copied

>>> from transformers.keras_callbacks import KerasMetricCallback

>>> metric_callback = KerasMetricCallback(metric_fn=compute_metrics, eval_dataset=tf_validation_set)

Specify where to push your model and tokenizer in the PushToHubCallback:

Copied

>>> from transformers.keras_callbacks import PushToHubCallback

>>> push_to_hub_callback = PushToHubCallback(
...     output_dir="my_awesome_opus_books_model",
...     tokenizer=tokenizer,
... )

Then bundle your callbacks together:

Copied

>>> callbacks = [metric_callback, push_to_hub_callback]

Finally, you’re ready to start training your model! Call fit with your training and validation datasets, the number of epochs, and your callbacks to finetune the model:

Copied

>>> model.fit(x=tf_train_set, validation_data=tf_test_set, epochs=3, callbacks=callbacks)

Once training is completed, your model is automatically uploaded to the Hub so everyone can use it!

For a more in-depth example of how to finetune a model for translation, take a look at the corresponding PyTorch notebook or TensorFlow notebook.

Inference

Great, now that you’ve finetuned a model, you can use it for inference!

Come up with some text you’d like to translate to another language. For T5, you need to prefix your input depending on the task you’re working on. For translation from English to French, you should prefix your input as shown below:

Copied

>>> text = "translate English to French: Legumes share resources with nitrogen-fixing bacteria."

The simplest way to try out your finetuned model for inference is to use it in a pipeline(). Instantiate a pipeline for translation with your model, and pass your text to it:

Copied

>>> from transformers import pipeline

>>> translator = pipeline("translation", model="my_awesome_opus_books_model")
>>> translator(text)
[{'translation_text': 'Legumes partagent des ressources avec des bactéries azotantes.'}]

You can also manually replicate the results of the pipeline if you’d like:

PytorchHide Pytorch content

Tokenize the text and return the input_ids as PyTorch tensors:

Copied

>>> from transformers import AutoTokenizer

>>> tokenizer = AutoTokenizer.from_pretrained("my_awesome_opus_books_model")
>>> inputs = tokenizer(text, return_tensors="pt").input_ids

Use the generate() method to create the translation. For more details about the different text generation strategies and parameters for controlling generation, check out the Text Generation API.

Copied

>>> from transformers import AutoModelForSeq2SeqLM

>>> model = AutoModelForSeq2SeqLM.from_pretrained("my_awesome_opus_books_model")
>>> outputs = model.generate(inputs, max_new_tokens=40, do_sample=True, top_k=30, top_p=0.95)

Decode the generated token ids back into text:

Copied

>>> tokenizer.decode(outputs[0], skip_special_tokens=True)
'Les lignées partagent des ressources avec des bactéries enfixant l'azote.'

TensorFlowHide TensorFlow content

Tokenize the text and return the input_ids as TensorFlow tensors:

Copied

>>> from transformers import AutoTokenizer

>>> tokenizer = AutoTokenizer.from_pretrained("my_awesome_opus_books_model")
>>> inputs = tokenizer(text, return_tensors="tf").input_ids

Use the generate() method to create the translation. For more details about the different text generation strategies and parameters for controlling generation, check out the Text Generation API.

Copied

>>> from transformers import TFAutoModelForSeq2SeqLM

>>> model = TFAutoModelForSeq2SeqLM.from_pretrained("my_awesome_opus_books_model")
>>> outputs = model.generate(inputs, max_new_tokens=40, do_sample=True, top_k=30, top_p=0.95)

Decode the generated token ids back into text:

Copied

>>> tokenizer.decode(outputs[0], skip_special_tokens=True)
'Les lugumes partagent les ressources avec des bactéries fixatrices d'azote.'
PreviousMasked language modelingNextSummarization

Last updated 1 year ago

🌍
🌍