Whistle, an on-device speech recognition model, trends on Hugging Face
Cactus-Compute · hf · 2026-10-05
Whistle, a speech recognition model from Cactus-Compute, is trending on Hugging Face. Built for on-device and edge deployment, it leverages WebAssembly and quantization to run speech-to-text locally, including in-browser, without cloud inference.
More from Infra
- llama.cpp merges new Metal kernels, making speculative decoding 3.4x faster on M3 Ultra — ggerganov · 2026-10-05
- Test equipment and laser lead times stretch up to a year as AI demand surges — zephyr_z9 · 2026-10-05
- Training Apex-2 for ~$2,000: dual GH200 + DiLoCo and 57% duplicate data lessons — Prestigious-Taste-63 · 2026-10-05
- Qualcomm licenses Huawei's LogicFolding chip tech in multiyear cross-license deal — teortaxesTex · 2026-10-05
- Tencent rents 100,000 Nvidia-class AI chips via Oracle abroad in $7B five-year deal — kimmonismus · 2026-10-05
- Solo dev open-sources MIR MEDIA LABS, a local AI media studio for NVIDIA GPUs — Da_QbanBeast · 2026-10-05