English to Portuguese, Spanish, German, Italian, French Translation

Saturday, August 26, 2023

Introducing SeamlessM4T, a Multimodal AI Model for Speech and Text Translations | Meta - Meta - Translation

The world we live in has never been more interconnected, giving people access to more multilingual content than ever before. This also makes the ability to communicate and understand information in any language increasingly important.

Today, we’re introducing SeamlessM4T, the first all-in-one multimodal and multilingual AI translation model that allows people to communicate effortlessly through speech and text across different languages. SeamlessM4T supports:

Speech recognition for nearly 100 languages
Speech-to-text translation for nearly 100 input and output languages
Speech-to-speech translation, supporting nearly 100 input languages and 36 (including English) output languages
Text-to-text translation for nearly 100 languages
Text-to-speech translation, supporting nearly 100 input languages and 35 (including English) output languages

In keeping with our approach to open science, we’re publicly releasing SeamlessM4T under a research license to allow researchers and developers to build on this work. We’re also releasing the metadata of SeamlessAlign, the biggest open multimodal translation dataset to date, totaling 270,000 hours of mined speech and text alignments.

Building a universal language translator, like the fictional Babel Fish in The Hitchhiker’s Guide to the Galaxy, is challenging because existing speech-to-speech and speech-to-text systems only cover a small fraction of the world’s languages. But we believe the work we’re announcing today is a significant step forward in this journey. Compared to approaches using separate models, SeamlessM4T’s single system approach reduces errors and delays, increasing the efficiency and quality of the translation process. This enables people who speak different languages to communicate with each other more effectively.

SeamlessM4T builds on advancements we and others have made over the years in the quest to create a universal translator. Last year, we released No Language Left Behind (NLLB), a text-to-text machine translation model that supports 200 languages, and has since been integrated into Wikipedia as one of the translation providers. We also shared a demo of our Universal Speech Translator, which was the first direct speech-to-speech translation system for Hokkien, a language without a widely used writing system. And earlier this year, we revealed Massively Multilingual Speech, which provides speech recognition, language identification and speech synthesis technology across more than 1,100 languages.

SeamlessM4T draws on findings from all of these projects to enable a multilingual and multimodal translation experience stemming from a single model, built across a wide range of spoken data sources with state-of-the-art results.

This is only the latest step in our ongoing effort to build AI-powered technology that helps connect people across languages. In the future, we want to explore how this foundational model can enable new communication capabilities — ultimately bringing us closer to a world where everyone can be understood.

Learn more about SeamlessM4T on our AI blog.

Adblock test (Why?)

Friday, August 25, 2023

What Doc Holliday Says To Johnny In Latin? Tombstone Scene Translation Explained - Screen Rant - Translation

[unable to retrieve full-text content]

What Doc Holliday Says To Johnny In Latin? Tombstone Scene Translation Explained Screen Rant

What Doc Holliday Says To Johnny In Latin? Tombstone Scene Translation Explained - Screen Rant - Translation

[unable to retrieve full-text content]

What Doc Holliday Says To Johnny In Latin? Tombstone Scene Translation Explained Screen Rant

20,000 words included in new dictionary of Shakespeare's English - Medievalists.net - Dictionary

The Arden Encyclopedia of Shakespeare’s Language, published this week, aims to be the ‘first fully corpus-based dictionary of Shakespeare’s language and most comprehensive since Alexander Schmidt’s in the early 1870s.’

William Shakespeare used the word dotage to capture reduced mental ability (as in being blindly in love) rather than as a quaint term for old age, successes were really outcomes – one could talk of a ‘bad success’ – and, it turns out, the word bastard back then most often referred to a flower that was genetically hybrid.

While dinner was preferred by Shakespeare for what we might think of as lunch (although his contemporaries used it to refer to an evening meal), beef, as today, was strongly associated with the English, but particularly the lower ranks (it was thought to reduce intelligence). And while fish was not only considered inferior to red meat, it was also considered to be ‘decidedly dodgy’, being associated with Catholicism or sex.

'To Kate' (v.) #cl2023
Quick peek inside the new @Ardenpublisher Encyclopedia of #Shakespeare Language
Every single word of his plays is included (minus proper nouns and numbers)! pic.twitter.com/cO46TeWzu4

— Katharine Kavanagh (@BustingFree) July 6, 2023

This new research by Lancaster University sheds light on the times with the publication of The Arden Encyclopedia of Shakespeare’s Language, published by Bloomsbury earlier this week. Its publication comes after 25 years of preparation, a £1 million Arts and Humanities Research Council grant, a team of up to 25 researchers, and seven years of hard work.

The project, conceived and led by Jonathan Culpeper, a Professor of English Language and Linguistics at Lancaster University, will result in a unique 5 volume reference work, detailing and illuminating Shakespeare’s rich language. A key feature of the project is that is uses corpus linguistics, the computer-aided analysis of massive datasets of language, to provide evidence-based accounts of Shakespeare’s language.

And not just of Shakespeare’s words. The volumes of the Encyclopedia will also reveal the linguistic thumbprints of plays and characters plays, the articulation of themes such as love and death, and the networks of character interaction. Professor Culpeper, who worked together with Dr Andrew Hardie and Dr Jane Demmen, also from Lancaster University, on these volumes, explains “This is the first fully corpus-based dictionary of Shakespeare’s language and most comprehensive since Alexander Schmidt’s in the early 1870s.”

This month sees the publication of the first two volumes, which together constitute a dictionary. Volumes 1 and 2 comprise 20,000 word-entries gleaned from a million-word corpus of Shakespeare’s plays and compared with a matching million-word corpus of contemporary plays, along with huge corpus of 320 million words of various writings of the period.

“So why the comparisons?” asks Professor Culpeper. “Other dictionaries define Shakespeare by looking just at Shakespeare. The result is a bit circular – Shakespeare’s words had lives amongst his contemporaries, and we pay attention to that, along with what they are doing in Shakespeare’s plays.”

It is obvious perhaps that wicked occurs densely in religious texts of the time, but who would have guessed that of the highly frequent word ourselves? Frequent words such as alas or ah are revealed to be heavily used by female characters, doing the emotional work of lamentation in the plays (especially histories).

“Frequent words,” Professor Culpeper comments, “often excluded from previous Shakespearean dictionaries, have a wood for the trees problem.”

The dictionary also surveys the infrequent, flagging words that occur but once in Shakespeare, such as bone-ache (syphilis) or ear-kissing (whispering, though other writers used it for flattering), and words that seem to have their earliest occurrence in Shakespeare (including, the decidedly modern-sounding self-harming).

The Encyclopedia is written for a general audience. The remaining volumes will be published over the next three years. To learn more, please visit the publisher’s website or buy this set on Amazon.com.

Being a small part of the @ShakespeareLang project was one of the highlights of my time at @LAEL_LU. Holding the encyclopedia for the first time earlier this week was really special. Congratulations to @j_culpeper, @HardieResearch and @JJDemmen on these first two volumes!! pic.twitter.com/3aoAtfych7

— Mathew Gillings (@mathewgillings) July 6, 2023

Top Image: Work on a new ‘verbal treasure trove’ captures nuances and uses of Shakespeare’s words. Phot courtesy Lancaster University, UK

Advertisement

Subscribe to Medievalverse

Adblock test (Why?)

Meta releases SeamlessM4T AI model for text and speech translation - Mashable - Translation

Meta's latest AI output is a major advancement for real-time text and speech translation.

On Tuesday, the company released SeamlessM4T: a multimodal model that translates text to speech and vice versa. Meta claims SeamlessM4T is "the first all-in-one multilingual multimodal AI translation and transcription model," meaning it is uniquely able to translate and transcribe languages at the same time. SeamlessM4T can translate speech-to-text, speech-to-speech, text-to-speech, and text-to-text inputs for up to 100 languages. Translations for speech-to-speech and text-to-speech translations outputs support 35 languages.

SEE ALSO: A giant online book collection Meta used to train its AI is gone over copyright issues

Tweet may have been deleted

Like other AI models recently released by Meta, including Llama 2 and AudioCraft, SeamlessM4T is publicly available for researchers and developers with a research license. Alongside the model, Meta is also releasing its training dataset called SeamlessAlign, which has 270,000 hours of speech and text alignments. Unlike OpenAI and Google, Meta has made a point of making its models open-source and publicly available. Meta's approach of launching open-source models has the dual effect of enabling developers to build and improve the products, while also winning points amongst AI ethicists who are calling for transparency of generative AI systems.

Meta's open-source approach may seem altruistic, but it's a strategic power move in a ruthlessly competitive market against other big tech companies developing AI. There's also the issue of data collection that all AI models must contend with. According to the blog post, SeamlessM4T's dataset (SeamlessAlign) consists of publicly available data, there are ethical and legal issues surrounding use of copyrighted works and personal data without consent.

Meta's announcement didn't detail specific plans for SeamlessM4T, only hinting that it wants "to explore how this foundational model can enable new communication capabilities." In other words, we might someday see a consumer-facing version of SeamlessM4T on WhatsApp or Instagram.

Topics Artificial Intelligence Meta

Adblock test (Why?)

Thursday, August 24, 2023

Meta releases AI model for translating speech between dozens of languages - Reuters - Translation

NEW YORK, Aug 22 (Reuters) - Facebook parent company Meta Platforms (META.O) on Tuesday released an AI model capable of translating and transcribing speech in dozens of languages, a potential building-block for tools enabling real-time communication across language divides.

The company said in a blog post that its SeamlessM4T model could support translations between text and speech in nearly 100 languages, as well as full speech-to-speech translation for 35 languages, combining technology that was previously available only in separate models.

CEO Mark Zuckerberg has said he envisions such tools facilitating interactions between users from around the globe in the metaverse, the set of interconnected virtual worlds on which he is betting the company's future.

Meta is making the model available to the public for non-commercial use, the blog post said.

The world's biggest social media company has released a flurry of mostly free AI models this year, including a large language model called Llama that poses a serious challenge to proprietary models sold by Microsoft-backed (MSFT.O) OpenAI and Alphabet's (GOOGL.O) Google.

Zuckerberg says an open AI ecosystem works to Meta's advantage, as the company has more to gain by effectively crowd-sourcing the creation of consumer-facing tools for its social platforms than by charging for access to the models.

Nonetheless, Meta faces similar legal questions as the rest of the industry around the training data ingested to create its models.

In July, comedian Sarah Silverman and two other authors filed copyright infringement lawsuits against both Meta and OpenAI, accusing the companies of using their books as training data without permission.

For the SeamlessM4T model, Meta researchers said in a research paper that they gathered audio training data from 4 million hours of "raw audio originating from a publicly available repository of crawled web data," without specifying which repository.

A Meta spokesperson did not respond to questions on the provenance of the audio data.

Text data came from datasets created last year that pulled content from Wikipedia and associated websites, the research paper said.

Reporting by Katie Paul, Editing by Rosalba O'Brien

Our Standards: The Thomson Reuters Trust Principles.

Acquire Licensing Rights, opens new tab

Adblock test (Why?)