hjLabs AI Playground
Starting the on-device runtime…
Whisper Base (Xenova) is a 74M-parameter ONNX model that transcribes speech from an audio file or a live microphone into text with timestamps. On this page it runs entirely inside your browser: the 141 MB download comes straight from the Hugging Face repository “Xenova/whisper-base” into your browser cache, and every inference after that executes on your own GPU through WebGPU. That is a one-off download of well under a minute on a normal connection, and small enough that integrated graphics handle it without complaint. The model is multilingual, so it is not restricted to English input.
The original Xenova conversion of Whisper Base — identical weights, and the only one here that also ships q4f16 for fp16-capable GPUs. In practice people reach for a model like this for transcribing interviews, meetings, voice notes and video soundtracks without uploading the audio anywhere.
Available precisions: fp32 (full precision), q8 (8-bit) and q4f16. fp32 comes first because at this size full precision is both the fastest WebGPU path and the best quality; the quantized variant exists for the WebAssembly fallback and for tight cache budgets. The f16 build only loads on adapters that report the WebGPU "shader-f16" feature, which many desktop GPUs — including NVIDIA cards under Linux Chrome — do not, so a non-f16 fallback is always listed after it. Hugging Face records around 166k downloads a month — steady, real usage rather than a one-off research drop.
Because there is no inference server behind this page, there is nothing to rate-limit and nothing to bill: the only cost of running Whisper Base (Xenova) here is the one-off 141 MB download, and once that is cached the page keeps working with the network switched off.
whisper base (xenova)whisper base (xenova) onnxwhisper base (xenova) browserrun whisper base (xenova) locallyxenova/whisper-basespeech to text modelwhisper base (xenova) webgpuwhisper base (xenova) download sizefree speech to text modeltransformers.js model
About 141 MB for the fp32 build, including the tokenizer and config files the runtime also has to fetch — this is the whole payload, not just the weights file. It is downloaded once and then served from the browser Cache Storage API.
Yes, through the WebAssembly fallback, which is slower but works anywhere. WebGPU (Chrome or Edge 113+, Safari 26+) is what makes it feel interactive. On WASM, prefer the smaller quantized build.
No. Xenova/whisper-base is a public repository, so your browser fetches the ONNX files directly over HTTPS. There is no account, no key and no server in between.
No. The model weights are downloaded from Hugging Face to your browser once, and every inference after that runs on your own GPU through WebGPU. Your text, images and audio are never sent anywhere — hjLabs.in has no inference server and no way to see your input.