Meta’s open-source speech AI recognizes over 4,000 spoken languages
, Meta is open-sourcing MMS today to help preserve language diversity and encourage researchers to build on its foundation. “Today, we are publicly sharing our models and code so that others in the research community can build upon our work,” the company wrote. “Through this work, we hope to make a small contribution to preserve the incredible language diversity of the world.”
Speech recognition and text-to-speech models typically require training on thousands of hours of audio with accompanying transcription labels. But for languages that aren’t widely used in industrialized nations — many of which are in danger of disappearing in the coming decades — “this data simply does not exist,” as Meta puts it.
Meta used an unconventional approach to collecting audio data: tapping into audio recordings of translated religious texts. “We turned to religious texts, such as the Bible, that have been translated in many different languages and whose translations have been widely studied for text-based language translation research,” the company said. “These translations have publicly available audio recordings of people reading these texts in different languages.
If you’re like me, that approach may raise your eyebrows at first glance, as it sounds like a recipe for an AI model heavily biased toward Christian worldviews. But Meta says that isn’t the case. “While the content of the audio recordings is religious, our analysis shows that this does not bias the model to produce more religious language,” Meta wrote.
Australia Latest News, Australia Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Meta reportedly wants to license Magic Leap’s AR technology | EngadgetMeta could turn to Magic Leap for help to stay ahead of Apple and other new entrants in the soon-to-be crowded AR space..
Read more »
Meta hit with $1.3 billion fine over Facebook's EU-US data transfers | EngadgetThe EU says Meta's policy of cross border data flows risks EU citizens' privacy..
Read more »
The Morning After: Meta could launch a Twitter competitor next month | EngadgetThe biggest news stories this morning: Apple rejected 1,679,694 App Store submissions in 2022, Meta could launch a Twitter competitor as early as next month, Disney’s pricey, immersive Star Wars hotel is shutting down..
Read more »
HP OfficeJet printers are bricking following a recent software update | EngadgetSince about the second week of May, the HP support forums have been rife with complaints of OfficeJet printers bricking after they automatically installed the company’s most recent firmware update..
Read more »
Western Digital promises to release firmware update for failing SanDisk Extreme SSDs | EngadgetWestern Digital says it will release a firmware update to address a reliability issue with its SanDisk Extreme and Extreme Pro SSDs..
Read more »
iMessage Contact Key Verification could arrive with iOS 16.6 | EngadgetApple first announced iMessage Contact Key Verification, a feature for protecting conversations from malicious actors, at the end of last year..
Read more »