Omar Sanseviero (@osanseviero)
새 모델이 성능 대비 크기 효율이 매우 뛰어나다고 소개하며, 지난 12개월간의 피드백을 반영해 추론 능력, 멀티모달 이해(OCR·음성 인식·객체 탐지), 긴 컨텍스트, 에이전트 기능 등을 크게 강화했다고 밝혔습니다. 구체적 모델명은 없지만 기술 업데이트 성격이 강합니다.
The team cooked a super impressive model, specially for the sizes! We've incorporated all the feedback from the last 12 months: thinking, expanded multimodal understanding (OCR, speech recognition, object detection), longer context, agentic, and more! https://t.co/llozjYtrkJ
https://winbuzzer.com/2026/03/27/cohere-open-source-transcribe-model-tops-asr-leaderboard-xcxwbn/
Cohere's Open-Source Transcribe Model Tops ASR Leaderboard
#AI #Cohere #CohereTranscribe #SpeechRecognition #AITranscription #OpenSourceAI #HuggingFace #MultimodalAI
AssemblyAI (@AssemblyAI)
의료 상담 음성인식에서 범용 ASR의 한계를 보완하기 위해, Universal-3 Pro 위에 동작하는 ‘Medical Mode’를 소개했다. 단일 파라미터로 활성화하며, 의료 용어 인식에 최적화된 보정 단계로 특정 약물명 같은 전문 용어 오인식을 줄이는 것이 핵심이다.
General-purpose ASR: 95%+ accuracy on a clinical consult. Also general-purpose ASR: gets "hydrochlorothiazide" wrong every time. Introducing Medical Mode — a correction pass on top of Universal-3 Pro optimized for medical entity recognition. Enable it with one parameter.
AssemblyAI (@AssemblyAI)
임상 워크플로우용 Medical Mode가 공개되었습니다. 일반적인 음성인식 정확도가 높아도 임상에서는 약물명 같은 핵심 토큰 오류 때문에 실사용이 어렵다는 문제를 해결하려는 기능입니다.
https://x.com/AssemblyAI/status/2036822463347302652
#medicalai #speechrecognition #clinicalworkflow #asr #healthcare
Medical Mode is now available for clinical workflows. We built Medical Mode because a transcript that's 95% accurate can still be unusable in a clinical setting. Errors in general-purpose ASR are often concentrated on exactly the tokens clinicians care about most: drug names,
Chrome extension adjusts video speed based on how fast the speaker is talking
https://github.com/ywong137/speech-speed
#HackerNews #ChromeExtension #VideoSpeed #SpeechRecognition #TechInnovation #OpenSource
Hands on with AI audio generation: GAI voice, music, and sound effects
This is the second post in a series exploring the multimodal possibilities of generative AI. This series will take a detailed, hype-free look at text, image, audio, video, and code generation and explore the creative potential as well as the ethical concerns of GAI. Although Generative AI isn't a new technology, it's definitely been having a hype moment since the release of ChatGPT in November 2022. Unfortunately, the focus has been squarely on the text-based chatbot at the exclusion of […]
https://winbuzzer.com/2026/03/16/ibm-granite-4-1b-speech-tops-openasr-leaderboard-xcxwbn/
IBM Granite 4.0 1B Speech Tops OpenASR Leaderboard
#AI #AIModels #IBM #SpeechRecognition #OpenSourceAI #EnterpriseAI #EdgeComputing #AITranslation #OpenASRLeaderboard
Nico Martin (@nic_o_martin)
MistralAI의 Voxtral과 Transformers.js, WebGPU 조합으로 브라우저에서 실시간 음성 전사가 가능해졌다는 발표입니다. 다양한 언어를 지원하며 문장 중간에 언어가 바뀌어도 인식하는 기능을 강조하여 웹 기반 ASR(자동 음성인식)의 저지연·다국어 적용 사례로 의미가 큽니다.
https://x.com/nic_o_martin/status/2032087412462022663
#mistralai #voxtral #transformersjs #webgpu #speechrecognition
sayzard
N-gated Hacker News
Winbuzzer
Sacha Chua
Hacker News
Leon Furze