Skip to content
AI NEWS JOURNAL
AI NEWS / SEARCH

News and site search

Explore related news, tools, models, guides, topics, workflows and prompts.

News stories 64

“Transcript AI”

News storiesarXiv cs.CL

CamSpokenNLI: A Pilot Resource for Cross-Variety Transfer Evaluation in Cameroon Pidgin English and Camfranglais

arXiv:2611.17573v1 Announce Type: new Abstract: Cameroon Pidgin English (a West African Pidgin English variety) and Camfranglais are widely used in Cameroon, yet to our knowledge, neither has a dedicated spoken Natural Language Inference (NLI) resource. We introduce CamSpokenNLI, a pilot dataset of 114 scenario-matched spoken NLI items in each variety (228 in total), recorded by one native speaker from Buea. Each item pairs premise audio and text with a hypothesis, an NLI label, and English glosses. The author assigned labels, so the dataset is an exploratory resource rather than a mature benchmark. The NLI experiments use the reference text; the audio is evaluated separately. XLM-RoBERTa baselines with five-fold item-level cross-validation reach 44.7% on Pidgin and 46.2% on Camfranglais (chance 33.3%). Still, neither is statistically distinguishable from hypothesis-only input, so hypothesis wording may account for much of the accuracy. Under disjoint-item cross-variety transfer, where a test item's counterpart is never seen in training, accuracy is 40.1% (Pidgin to Camfranglais) and 45.6% (Camfranglais to Pidgin). A counterpart-leak audit raises this to 60-64%, illustrating how counterpart leakage can overstate transfer. Zero-shot Whisper transcription of the recordings performs poorly: the best word error rates are 66.6% for Pidgin and 45.5% for Camfranglais, and with automatic language identification, Whisper Large-v3 labels 93 of 114 Pidgin recordings as Yoruba or Swahili. Together, the results suggest that such resources need disjoint-item evaluation and hypothesis-only controls, and that speech recognition must be adapted to these varieties before spoken NLI can be tested end to end.

Read story ↗
News storiesHacker News Show HN

Show HN: Redacted - Stop Handing Claude Your Secrets

Article URL: https://github.com/svn-arv/redacted/ Comments URL: https://news.ycombinator.com/item?id=50513298 Points: 1 # Comments: 0

Read story ↗
News storiesHacker News Show HN

Show HN: AI Time Estimator – how long Claude Code will take, from your own logs

Article URL: https://github.com/noambrand/ai-time-estimator Comments URL: https://news.ycombinator.com/item?id=50499487 Points: 2 # Comments: 0

Read story ↗
News storiesHacker News Show HN

Show HN: Linux CLI for Cricut StickerPix

Article URL: https://github.com/vavkamil/crycut Comments URL: https://news.ycombinator.com/item?id=50498398 Points: 1 # Comments: 0

Read story ↗
News storiesAWS Machine Learning Blog

Cost-optimizing AssemblyAI speech-to-text inference on AWS with Amazon EC2 Spot

Learn how AssemblyAI runs cost-optimized speech-to-text inference at scale on AWS, using Amazon ECS, Amazon EC2 Spot GPU instances, and an Amazon SQS-based retry architecture to achieve 70% cost savings while maintaining SLA commitments across European Regions.

Read story ↗
News storiesAWS Machine Learning Blog

Route coding agent requests to the right model on Amazon Bedrock with NVIDIA NeMo Switchyard

Coding agents work in tasks, and the number that matters is cost per solved task, not price per token. In this post, you use the AWS CDK to deploy LiteLLM with the NVIDIA NeMo Switchyard routing plugin on Amazon Bedrock, then measure cost per solved task for a routed model group against single-model baselines.

Read story ↗
News storiesHacker News Show HN

Show HN: Audio Transcription in Browser with WebGPU

Article URL: https://whisper.tanpreet.xyz/demo/ Comments URL: https://news.ycombinator.com/item?id=50495635 Points: 1 # Comments: 0

Read story ↗
News storiesHacker News Show HN

Show HN: Memro – Persistent Memory for Claude Code, Cursor and Codex

Memro is go bases persistent memory system that lets ai agents share context acssion session using mcp, built on top of postgreSQL Comments URL: https://news.ycombinator.com/item?id=50492093 Points: 2 # Comments: 1

Read story ↗
News storiesClickHouse

Introducing Loom: agent memory that keeps up with your code

Loom gives coding agents shared memory and a code index grounded in the repository, so each session can build on what the last one learned.

Read story ↗
News storiesMicrosoft Research

Microsoft Research Focus – Edition #98

What's new in research at Microsoft? Host Anson Ho explores the latest, including AI-powered universal translation, a breakthrough in a 31-year-old mathematics challenge, and advances making AI coding agents faster and more efficient. The post Microsoft Research Focus – Edition #98 appeared first on Microsoft Research.

Read story ↗