Awesome

SONAR

[Paper] [Demo]

We introduce SONAR, a new multilingual and multimodal fixed-size sentence embedding space, with a full suite of speech and text encoders and decoders. It substantially outperforms existing sentence embeddings such as LASER3 and LabSE on the xsim and xsim++ multilingual similarity search tasks.

Speech segments can be embedded in the same SONAR embedding space using language-specific speech encoders trained in a teacher-student setting on speech transcription data. We also provide a single text decoder, which allows us to perform text-to-text and speech-to-text machine translation, including for zero-shot language and modality combinations.

SONAR stands for Sentence-level multimOdal and laNguage-Agnostic Representations

The full list of supported languages (along with download links) can be found here below.

SONAR Architecture:

Text results

Speech results

Installing

You can install SONAR with pip install sonar-space. Note that there is another sonar package on pip that IS NOT this project, make sure to use sonar-space in your dependencies.

SONAR depends on fairseq2 and torch/torchaudio, you will have to install the variant (cpu/cuda/...) that works for your environment manully.

Check fairseq2 variants for possible variants. Note that SONAR currently relies on the release candidate for fairseq2 0.3.0 rc1.

If fairseq2 does not provide a build for your machine, check the readme of that project to build it locally.

Usage

fairseq2 will automatically download models into your $TORCH_HOME/hub directory upon using the commands below.

Compute text sentence embeddings with SONAR:

from sonar.inference_pipelines.text import TextToEmbeddingModelPipeline
t2vec_model = TextToEmbeddingModelPipeline(encoder="text_sonar_basic_encoder",
                                           tokenizer="text_sonar_basic_encoder")
sentences = ['My name is SONAR.', 'I can embed the sentences into vectorial space.']
embeddings = t2vec_model.predict(sentences, source_lang="eng_Latn")
print(embeddings.shape)
# torch.Size([2, 1024])

Reconstruct text from SONAR embeddings

from sonar.inference_pipelines.text import EmbeddingToTextModelPipeline
vec2text_model = EmbeddingToTextModelPipeline(decoder="text_sonar_basic_decoder",
                                              tokenizer="text_sonar_basic_encoder")
reconstructed = vec2text_model.predict(embeddings, target_lang="eng_Latn", max_seq_len=512)
# max_seq_len is a keyword argument passed to the fairseq2 BeamSearchSeq2SeqGenerator.
print(reconstructed)
# ['My name is SONAR.', 'I can embed the sentences into vector space.']

Translate text with SONAR

from sonar.inference_pipelines.text import TextToTextModelPipeline
t2t_model = TextToTextModelPipeline(encoder="text_sonar_basic_encoder",
                                    decoder="text_sonar_basic_decoder",
                                    tokenizer="text_sonar_basic_encoder")  # tokenizer is attached to both encoder and decoder cards

sentences = ['My name is SONAR.', 'I can embed the sentences into vectorial space.']
t2t_model.predict(sentences, source_lang="eng_Latn", target_lang="fra_Latn")
# ['Mon nom est SONAR.', "Je peux intégrer les phrases dans l'espace vectoriel."]

Compute speech sentence embeddings with SONAR

from sonar.inference_pipelines.speech import SpeechToEmbeddingModelPipeline
s2vec_model = SpeechToEmbeddingModelPipeline(encoder="sonar_speech_encoder_eng")

s2vec_model.predict(["./tests/integration_tests/data/audio_files/audio_1.wav",
                     "./tests/integration_tests/data/audio_files/audio_2.wav"]).shape
# torch.Size([2, 1024])
import torchaudio
inp, sr = torchaudio.load("./tests/integration_tests/data/audio_files/audio_1.wav")
assert sr == 16000, "Sample rate should be 16kHz"

s2vec_model.predict([inp]).shape
# torch.Size([1, 1024])

Speech-to-text translation with SONAR

from sonar.inference_pipelines.speech import SpeechToTextModelPipeline

s2t_model = SpeechToTextModelPipeline(encoder="sonar_speech_encoder_eng",
                                      decoder="text_sonar_basic_decoder",
                                      tokenizer="text_sonar_basic_decoder")

import torchaudio
inp, sr = torchaudio.load("./tests/integration_tests/data/audio_files/audio_1.wav")
assert sr == 16000, "Sample rate should be 16kHz"

# passing loaded audio files
s2t_model.predict([inp], target_lang="eng_Latn")
# ['Television reports show white smoke coming from the plant.']

# passing multiple wav files 
s2t_model.predict(["./tests/integration_tests/data/audio_files/audio_1.wav",
                   "./tests/integration_tests/data/audio_files/audio_2.wav"], target_lang="eng_Latn")
# ['Television reports show white smoke coming from the plant.',
# 'These couples may choose to make an adoption plan for their baby.']

Predicting sentence similarity with BLASER 2.0 models

BLASER 2.0 is a family of models for automatic evaluation of machine translation quality based on SONAR embeddings. They predict cross-lingual semantic similarity between the translation and the source (optionally, also using a reference translation).

from sonar.inference_pipelines.text import TextToEmbeddingModelPipeline
from sonar.models.blaser.loader import load_blaser_model

blaser_ref = load_blaser_model("blaser_2_0_ref").eval()
blaser_qe = load_blaser_model("blaser_2_0_qe").eval()
text_embedder = TextToEmbeddingModelPipeline(encoder="text_sonar_basic_encoder", tokenizer="text_sonar_basic_encoder")

src_embs = text_embedder.predict(["Le chat s'assit sur le tapis."], source_lang="fra_Latn")
ref_embs = text_embedder.predict(["The cat sat on the mat."], source_lang="eng_Latn")
mt_embs = text_embedder.predict(["The cat sat down on the carpet."], source_lang="eng_Latn")

print(blaser_ref(src=src_embs, ref=ref_embs, mt=mt_embs).item())  # 4.688
print(blaser_qe(src=src_embs, mt=mt_embs).item())  # 4.708

Detailed model cards with more examples: facebook/blaser-2.0-ref, facebook/blaser-2.0-qe.

Classifying the toxicity of sentences with MuTox

MuTox, the first highly multilingual audio-based classifier (binary) and dataset with toxicity labels. The dataset consists of 20k audio utterances for English and Spanish, and 4k for the other 19 languages, and uses the multi-model and multilingual encoders from SONAR. The output of the MuTox classifier is a logit of the evaluated being "toxic", according to the definition adopted in the corresponding dataset.

from sonar.models.mutox.loader import load_mutox_model
from sonar.inference_pipelines.text import TextToEmbeddingModelPipeline
import torch

if torch.cuda.is_available():
    device = torch.device("cuda:0")
    dtype = torch.float16
else:
    device = torch.device("cpu")
    dtype = torch.float32

t2vec_model = TextToEmbeddingModelPipeline(
    encoder="text_sonar_basic_encoder",
    tokenizer="text_sonar_basic_encoder",
    device=device,
)
text_column='lang_txt'
classifier = load_mutox_model(
    "sonar_mutox",
    device=device,
    dtype=dtype,
).eval()

with torch.inference_mode():
    emb = t2vec_model.predict(["De peur que le pays ne se prostitue et ne se remplisse de crimes."], source_lang='fra_Latn')
    x = classifier(emb.to(device).to(dtype)) # tensor([[-19.7812]], device='cuda:0', dtype=torch.float16)

with torch.inference_mode():
    emb = t2vec_model.predict(["She worked hard and made a significant contribution to the team."], source_lang='eng_Latn')
    x = classifier(emb.to(device).to(dtype)) # tensor([[-53.5938]], device='cuda:0', dtype=torch.float16)

with torch.inference_mode():
    emb = t2vec_model.predict(["El no tiene ni el más mínimo talento, todo lo que ha logrado ha sido gracias a sobornos y manipulaciones."], source_lang='spa_Latn')
    x = classifier(emb.to(device).to(dtype)) # tensor([[-21.4062]], device='cuda:0', dtype=torch.float16)

For a CLI way of running the MuTox pipeline, go to Seamless Communication/.../MuTox.

Demo notebooks

See more complete demo notebooks :

• sonar text2text similarity and translation
• sonar speech2text and other data pipeline examples
• sonar bilingual document alignment with sonar text similarity

Supported languages and download links

The SONAR text encoder & decoder supports 200 languages. SONAR speech encoders support 37 languages.

All 200 languages from the No Language Left Behind project are supported.

Citation Information

Please cite the paper when referencing the SONAR embedding space, encoders and decoders as:

@misc{Duquenne:2023:sonar_arxiv,
  author = {Paul-Ambroise Duquenne and Holger Schwenk and Benoit Sagot},
  title = {{SONAR:} Sentence-Level Multimodal and Language-Agnostic Representations},
  publisher = {arXiv},
  year = {2023},
  url = {https://arxiv.org/abs/2308.11466},
}

Contributing

See the CONTRIBUTING file for how to help out.

License

SONAR code is released under the MIT license (see CODE_LICENSE).

Some of SONAR models are released with the same MIT license, BUT BEWARE, some of them are released under a non commercial license (see NC_MODEL_LICENSE). Please refer to LICENSE for the details.