SShortSingh.
Back to feed

Offline browser app identifies bird species from calls using local AI

0
·1 views

A developer has created a web application called Touch Grass Birder that identifies bird species from audio recordings entirely within a user's browser. The tool uses the open BirdNET v2.4 model to recognize 6,522 species and runs locally via ONNX Runtime WebAssembly, requiring no internet connection after initial setup. It is designed for situations where birdwatchers lack cellular service, enabling identification through a six-second recording. The application is fully open-source and prioritizes minimizing screen time by instructing users to immediately pocket their devices after receiving results.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

Log in to join the discussion and vote.

Log in

Related stories

0
ProgrammingHacker News ·

AI's Unpredictable Behavior Compared to 'Roadside Picnic' Sci-Fi Scenario

An article on MeteData uses the science fiction novel 'Roadside Picnic' to frame the discussion of unpredictable AI behavior. The novel describes an alien visitation zone with inexplicable and dangerous artifacts, which the author compares to the unexpected and often opaque outputs of modern AI systems. The piece, shared on Hacker News, has garnered community discussion with several comments. The comparison aims to explore the challenges of understanding and managing complex, non-human intelligence.

0
ProgrammingDEV Community ·

Developer analyzes $320 million ransom negotiation details from terminal

A developer named Davi de Jesus detailed an analysis of a $320 million ransom negotiation. The analysis was performed from a computer terminal and posted on September 8. It involved examining data related to a significant digital ransom demand. The technical exploration, shared on DEV Community, touched on topics including Bitcoin, Python, security, and open-source software.

0
ProgrammingDEV Community ·

Independent review finds SupaVoxel outperforms Tripo AI in 3D model generation test

An independent reviewer tested two AI 3D modeling services, Tripo AI and SupaVoxel, using the same source image of a skull ornament. The reviewer generated models using each service's default settings and analyzed the resulting files for printability. Tripo's model was significantly larger and more expensive in credits but introduced unwanted wood-grain texture into the geometry. SupaVoxel's model was smaller, cheaper, and produced a cleaner mesh, though it required some repair for shell structure. The reviewer concluded SupaVoxel's output was preferable for 3D printing the specific test object.

0
ProgrammingDEV Community ·

Tutorial: Building a Competitive Intelligence Agent for Public Companies

A developer tutorial proposes building a competitive intelligence agent for public companies. The agent is designed to gather and synthesize data from sources like SEC filings, news, and market data. It aims to extract strategic signals and produce a cited brief for human review. The workflow is implemented in TypeScript and uses the Valyu API for data retrieval. The tool is intended for research purposes and explicitly avoids providing investment advice.