Faster streaming speech recognition on @Arm edge devices: see how ExecuTorch, SME2, FP16 and QC8W balance accuracy and latency—delivering up to 2.12× faster processing on Pixel 11. Read our latest blog: ✍ Josiah Davis, Kshitij Sisodia

A new speech-to-text model of only 1.06MB can transcribe audio ~436× faster than real time on ONE CPU thread! No GPU. AuroraASR-1M is a super super small local speech-recognition model with these stats 🧠 949K parameters 💾 FP32 → 3.81MB 💾 FP16 → 1.91MB 💾 INT8 → 1.06MB 🔓 Apache 2.0 🖥️ CPU or GPU The developer measured the full end-to-end pipeline — feature extraction + speech recognition + CTC decoding at ... 🖥️ 1 CPU thread → ~436× real time 🔥 RTX PRO 6000 Blackwell → ~1,362× real time 🎯So 10 minutes of audio could be processed in about 1.4 seconds at the reported single-thread CPU rate. So to underscore, this isn't using an external language model! It's a tiny Conformer-CTC model trained on LibriSpeech and can run through Transformers locally. There's a tradeoff, accuracy AuroraASR-1M test-clean WER → 11.43% Whisper Tiny English → 5.6% So Whisper Tiny is substantially more accurate. Aurora is also 🇺🇸 English only 🔡 lowercase output ❌ no punctuation A 1MB model can now turn speech into text locally at hundreds of times real time on a single CPU core. That makes completely offline transcription, voice commands and embedded voice features almost absurdly cheap. 🔗 Hugging Face model in ALT.

Audio8 ASR Infinite streaming speech recognition model the native streaming architecture decodes 12.5 times per second a rolling KV Cache keeps both memory and latency constant, even in 24/7 operation one text token per clock step (12.5 / 8.3 / 6.25 decisions per second), balancing perception granularity and resource cost ML intern in huggingchat setup a gradio workflow to try it out: huggingchat: model:

We’re proud to share that Meta Omnilingual Automatic Speech Recognition (ASR) has been named one of @TIME’s Best Inventions of 2026! Meta Omnilingual ASR is 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 well-represented on the internet, this release marked a major step toward building a truly universal transcription system. Learn more about it here:

Join Nebius on October 1 for Building and Evaluating Clinical Speech AI. Learn how to deploy Nemotron Speech on Nebius while adapting speech recognition to medical terminology and maintaining privacy within clinical workflows. Register:

🤖 Powerful AI empowerment workshop in Macau this week From Cantonese speech recognition to faster administrative approvals and smarter healthcare — the workshop proved that real AI value comes from solving local problems. 💪 Interested in how AI can work for your business in Macau? Let's connect: #AlibabaCloudISV# #AIforMacau# #AInnovation#

🌍Introducing Hy ASR 3.0 preview, a speech recognition model from @TencentHunyuan built to understand, not just transcribe What we improved: - Cleaner on real-world audio: dialects, code-switching, and long-form content with less error accumulation over time - Context-aware correction: homophones and ambiguous phrases get resolved from context, not guessed in isolation - Hotword injection: drop in brand names, people, domain terms without retraining. Lowers integration cost for niche use cases - Built for noisy rooms: whisper, background noise, tricky acoustic conditions stay stable

Students from the UAE built Líng Huà, an Arabic-first Mandarin learning platform powered by Huawei Cloud AI. It removes the need to translate through English, using speech recognition, AI scoring, and translation to help learners develop Mandarin skills intuitively.

So, you could build Windows apps that run a GGUF model right on the PC without a separately running model server. Microsoft is adding experimental llama.cpp support to Windows ML, its toolkit for developers building local AI into Windows apps. So basically, bring your own model. Run inference locally. For example, connect speech recognition to text generation. More everyday apps using models on hardware you own. But this is an early implementation 🖥️ GGUF support validated on CPU and NVIDIA CUDA 🚫 No GGUF-to-NPU support ⚠️ The new text-generation API currently lacks temperature sampling, chat templates and speculative decoding llama.cpp does the inference underneath. Windows ML provides the application interfaces around it. Link in ALT.