Experiments With GCP's Chirp: An Example Of Multilingual Transcription
Television news across the world frequently contains excerpts of languages other than the dominate language of the broadcast, either through…
More Experiments Visually Describing TV News Using Google's Imagen Generative AI Image Captioning
Earlier this month we examined Imagen on Vertex AI, Google's new image-based generative AI foundational model for images, applying it to…
The Challenges Of LLM-Powered Code Generators: Early Observations From The Trenches
A growing body of research is beginning to call into question the quality of LLM-generated code, even as the tech…
Major New Chirp Demo Coming Soon
Stay tuned for a massive new demo of Chirp applied to the Visual Explorer!
Modern Monetary Theory (MMT) Has Faded In The Media
Modern Monetary Theory (MMT) rocketed into the media limelight in January 2019, peaking in March of that year and remaining…
Getting Started With GCP's Chirp / Universal Speech Model (USM) Multilingual Speech Transcription: Transcribing A 2.5 Hour Russian Broadcast In 4 Minutes
How can you leverage GCP's powerful Universal Speech Model (USM) known as "Chirp" for multilingual speech transcription? USM is a "family…
CEPR: Black Tulips And The Russian War In Ukraine
A look at protests and coverage of casualties in Russia's invasion of Ukraine. Read The Full Article.
Slator: Meta Debuts SeamlessM4T, The Swiss Army Knife Of Translation Models
Slator referenced our analyses of Meta's new SeamlessM4T model in their coverage of its release. Read The Full Article.
Experiments With Speech Transcription & Translation: Meta's SeamlessM4T Vs OpenAI's Whisper Vs GCP's STT+GT Vs GCP's USM/Chirp+GT
As the final piece in our our series of evaluating Meta's new SeamlessM4T multimodal translation model, let's evaluate its speech transcription and…
Experiments With Meta's SeamlessM4T Open Machine Translation Model: Medium Model Outperforming Large Model
Continuing our series of evaluating Meta's new SeamlessM4T multimodal translation model, there are actually two versions of the model: large and medium. We've…
Experiments With Meta's SeamlessM4T Open Machine Translation Model: News Articles
Continuing our series of evaluating Meta's new SeamlessM4T multimodal translation model, let's expand our social media experiments with a full-length news article. While…
Experiments With Meta's SeamlessM4T Open Machine Translation Model: Social Media Posts
Continuing our series of evaluating Meta's new SeamlessM4T multimodal translation model. Let's try translating some Weibo social media posts that…
Experiments With Meta's SeamlessM4T Open Machine Translation Model: Government Publication Translations
Yesterday, Meta announced its new SeamlessM4T multimodal translation model. Let's run a quick simple benchmark of its textual Chinese to…
WashPost: Debate Or Not, Fox News Is Still Trump Territory
The Washington Post's Philip Bump examines media coverage of the GOP presidential candidates. Read The Full Article.
Miami Herald: From Backbench Congressman To Debate Limelight: The Rise Of Ron DeSantis, Soundbite By Soundbite
This fascinating and extensive analysis by the Miami Herald includes a number of findings from the TV Explorer. Read The…
Introducing Television News Monitoring For All: A New Pipeline For Instant Monitoring Of Breaking Global Events
The Internet Archive's Television News Archive encompasses over 9.5 million broadcasts totaling 6.6 million hours of airtime from 108 television…
LLM-Based Landscape Summarization Demos Coming Soon
Stay tuned for some exciting new demos coming soon combining GDELT's datasets with a series of LLM pipelines for global…
Updated Donald Trump Airtime Analysis Coming Soon
Stay tuned for an updated workflow tracking Donald Trump appearances coming soon.
GCP USM/Chirp ASR Tutorial Coming Next Week
Stay tuned for a new tutorial on using GCP's USM/Chirp ASR model next week!
New Television News Monitoring Workflow Coming Next Week
Stay tuned for a major new announcement about television news monitoring coming next week!
DOC 2.0 API + LLMs = Summarizing Headlines: Turkish Investment, Inflation & The Niger Coup
The DOC 2.0 API allows rich keyword search over English machine translations of GDELT's online news monitoring in 65 languages….
Extracting & Codifying Disease Outbreaks Using LLMs: Experiments With Bison, ChatGPT & Claude
Earlier this year we explored the use of LLMs for disease extraction and codification tasks from news coverage, testing how…
How Are Africans Talking About Climate Change And Who Is Doing The Talking?
This study identifies who is talking about climate change in Africa, both in the mainstream media and on Twitter, and…
Visually Describing TV News Broadcasts Using Generative AI Image Captioning: Experiments With Google's New Imagen
With the recent release into general availability of Imagen on Vertex AI, Google's new image-based generative AI foundational model for…