# YazSes and Hugging Face

Hugging Face shows up in three different roles around YazSes. They have different privacy
properties, so this page keeps them apart.

## 1. The installed app: Hugging Face is where the model comes from

YazSes on your computer recognises speech **locally**, on your own CPU. It needs no
account, no subscription and no cloud inference API.

The one time it uses the network is to fetch the speech model. The default models are
open [faster-whisper](https://github.com/SYSTRAN/faster-whisper) conversions published by
SYSTRAN on the Hugging Face Hub. After that single download, dictation works with the
network off. Which models, and how to install one by hand on a machine that cannot reach
the Hub, is on [Models](models.md); every network connection YazSes can make is listed on
the [privacy statement](privacy-statement.md).

YazSes does not train these models, and using the Hub as a download host does not make
Hugging Face the maintainer of YazSes. Each model's own licence and terms apply to it.

## 2. The hosted demo: audio *does* leave your computer

There is one YazSes page on Hugging Face that runs speech recognition for you:

**[YazSes hosted transcription demo](https://huggingface.co/spaces/mskazemi/yazses-offline-transcription-demo)**

!!! warning "This is not the private, offline app"
    This is a hosted demonstration. Audio submitted here is processed on Hugging Face
    infrastructure. For private, offline voice typing, install YazSes on your own computer.

What it is for, and what it is not:

| | Hosted demo (Hugging Face Space) | YazSes installed on your computer |
|---|---|---|
| Where speech is processed | Hugging Face servers | Your own CPU |
| Does your audio leave your computer? | **Yes** | No (the model is downloaded once, then nothing leaves) |
| Hold-to-talk anywhere on the desktop | No | Yes |
| Types into the focused application | No | Yes |
| Purpose | Judge transcription quality before installing | Everyday dictation |

The demo uses the same engine family and the same default model size as the desktop app
(faster-whisper `base.en`, CPU, `int8`), but it is **not** the same pipeline, so a
transcript there is an indication of accuracy, not a guarantee of what the app would type.
It trims silence with the decoder's voice-activity filter, which the desktop app
deliberately does not use, and it applies none of the app's text post-processing.

It accepts recordings of up to 60 seconds and 25 MB, and refuses longer or unreadable
files with a message. Its code adds no logging or analytics of its own and writes no audio
or transcripts anywhere. Gradio, the framework it runs on, does keep each recording or upload
in a temporary cache on the server: the Space checks that cache every 10 minutes and deletes
files older than 10 minutes, so a recording can stay there for up to about 20 minutes. It
makes no promise about what Hugging Face itself logs or keeps; that is governed by Hugging
Face's own policies.

## 3. Research and source

- **GitHub is the canonical home** of the source code, the issue tracker and every
  contribution: <https://github.com/MSKazemi/yazses>.
- **The first paper**, *YazSes: An Offline, Privacy-First, Cross-Platform Hold-to-Talk
  Voice-Dictation System* ([arXiv:2607.28878](https://arxiv.org/abs/2607.28878)),
  describes the system. Cite it, or the software's concept DOI, as `CITATION.cff` says.
- **Benchmark results** behind the published numbers are archived as JSON in
  [`paper/results/`](https://github.com/MSKazemi/yazses/tree/main/paper/results), with a
  [manifest](https://github.com/MSKazemi/yazses/blob/main/paper/results/MANIFEST.md) naming the
  machine each one was taken on. Two numbers are comparable only if their machine matches.
  The method and headline results are on [Benchmarks](benchmarks.md).

## The rest of the Hub presence

The project's official organization is [huggingface.co/yazses](https://huggingface.co/yazses); it holds a short
introduction. The pages below live under the maintainer's own account, [huggingface.co/mskazemi](https://huggingface.co/mskazemi):

| Page | What it is |
|---|---|
| [Showcase Space](https://huggingface.co/spaces/mskazemi/yazses-showcase) | A static one-page overview. It does not run YazSes and processes no audio |
| [Benchmark results dataset](https://huggingface.co/datasets/mskazemi/yazses-benchmark-results) | The archived results as plain CSV tables with provenance (machine, versions, corpus), under a dataset card. It contains no audio, no transcripts and no corpus text |
| [Research collection](https://huggingface.co/collections/yazses/yazses-offline-speech-recognition-research) | A curated list: the paper, the demo, the showcase, the dataset and the upstream models |
| [Paper page](https://huggingface.co/papers/2607.28878) | The Hub's page for the arXiv preprint, linked to the dataset and the Spaces that cite it |

The files behind these pages live in the repository's [`huggingface/`](https://github.com/MSKazemi/yazses/tree/main/huggingface)
directory, which is their source of truth. The pages online today were first put up, and
later moved or renamed, outside the publishing workflow; from now on, changes are published
through that workflow rather than edited on the Hub. The files are checked offline by
`scripts/hf_preflight.py` before anything can go out, and the benchmark tables are
regenerated from the archive by `scripts/export_hf_benchmarks.py` (`--check` fails on
drift). The publishing workflow is manual-only, uses Hugging Face Trusted Publishers with
short-lived credentials rather than a stored token, and refuses any destination the
maintainer has not approved in a reviewed commit.

## Related

- [Try it without installing](try-without-installing.md): Docker, the hosted demo and Codespaces
- [Models](models.md): which speech models YazSes can run
- [Privacy statement](privacy-statement.md)
- [Benchmarks](benchmarks.md)