IBM ships a 470M Granite Speech model for fast edge transcription
IBM released Granite Speech 5.0 TurboCTC, a 470M-parameter English speech-recognition model under Apache 2.0. The encoder-only model is supported in Transformers, has a WebGPU demo, and is designed for low-latency or high-throughput transcription rather than translation or keyword-biased speech tasks.
Why it matters: A small, permissively licensed speech model creates a practical route to private laptop, browser, phone, or batch transcription. Its narrow task scope also makes evaluation clearer than a general speech-language model: word error rate, speed, memory, noise,…