/
Navigation
Chronicles
Browse all articles
Explore
Semantic exploration
Research
Entity momentum
Nexus
Correlations & relationships
Story Arc
Topic evolution
Drift Map
Semantic trajectory animation
Posts
Analysis & commentary
Pulse API
Tech news intelligence API
Browse
Entities
Companies, people, products, technologies
Domains
Browse by publication source
Handles
Browse by social media handle
Detection
Concept Search
Semantic similarity search
High Impact Stories
Top coverage by position
Sentiment Analysis
Positive/negative coverage
Anomaly Detection
Unusual coverage patterns
Analysis
Rivalry Report
Compare two entities head-to-head
Semantic Pivots
Narrative discontinuities
Crisis Response
Event recovery patterns
Connected
Search: /
Command: ⌘K
Embeddings: large
TEXXR ▲
TEXXR

Chronicles

The story behind the story

← → days · ↑ ↓ browse · Enter similar · o open

Meta releases Omnilingual Automatic Speech Recognition, a suite of AI models handling automatic speech recognition for 1,600+ languages, vs. OpenAI Whisper's 99

models that understand 1,600+ languages, including 500 that have never been supported before! 🤯 - <10% character error rate for 78% of languages -In-context learning: adapt to new languages with only a few audio samples -Model: [image] Wessel van Keulen / @wesselvk : @AIatMeta I'm really impressed with the progress made with such limited data / voice. @aiatmeta : Introducing Meta Omnilingual Automatic Speech Recognition (ASR), a suite of models providing ASR capabilities for over 1,600 languages, including 500 low-coverage languages never before served by any ASR system. While most ASR systems focus on a limited set of languages that are [video] Forums: Hacker News : Omnilingual ASR: Advancing automatic speech recognition for 1600 languages

VentureBeat Carl Franzen

Related Coverage

Discussion

  • @altryne Alex Volkov on x
    WHOA this is big, Meta releases a new speech recognition model that supposedly covers over 1,600 languages (up to 5400 with one shot learning!) by comparison, Whisper supports over 90 stated and around 57 actually [...] All under apache 2.0 license!
  • @wjb_mattingly William J.B. Mattingly on x
    Woah! Omnilingual ASR from Meta! As someone who works in low-resource language ASR, this looks incredible. Will certainly be testing this week!! [image]
  • @alexandr_wang Alexandr Wang on x
    Meta Omnilingual ASR expands speech recognition to 1,600+ languages, including 500 never before supported, as a major step towards truly universal AI. We are open-sourcing a full suite of models and a dataset: https://github.com/...
  • @tu7uruu Steven on x
    Wow. Meta just released Omnilingual ASR — models that understand 1,600+ languages, including 500 that have never been supported before! 🤯 - <10% character error rate for 78% of languages -In-context learning: adapt to new languages with only a few audio samples -Model: [image]
  • @wesselvk Wessel van Keulen on x
    @AIatMeta I'm really impressed with the progress made with such limited data / voice.
  • @aiatmeta @aiatmeta on x
    Introducing Meta Omnilingual Automatic Speech Recognition (ASR), a suite of models providing ASR capabilities for over 1,600 languages, including 500 low-coverage languages never before served by any ASR system. While most ASR systems focus on a limited set of languages that are …