---
license: other
license_name: model-specific
license_link: https://huggingface.co/hacksider/snaptop-models/blob/main/LICENSES.md
tags:
  - snaptop
  - sam3
  - onnx
  - speech
  - ocr
---

# SnapTop model catalog

The dedicated public model repository for SnapTop, separate from application source and all other account repositories.
All SnapTop model downloads originate here. Files are public; no account, login or access token is needed.
Models run locally: screenshots, recordings, prompts and voice samples remain on the user's computer.

SnapTop downloads models on demand using the immutable commit and SHA-256 checksums recorded in the application's `sam/model-source.json`.
`MODEL_CATALOG.json` records file sizes, checksums and exact upstream revisions. `SHA256SUMS` covers all distributed model payloads.
Each model folder includes its original license and provenance. The licenses are model-specific; this repository does not relicense model weights.

## SAM3

The root `model.safetensors` and processor/tokenizer files are unchanged Meta SAM3 weights from
[facebook/sam3@3c879f39826c281e95690f02c7821c4de09afae7](https://huggingface.co/facebook/sam3/tree/3c879f39826c281e95690f02c7821c4de09afae7).
The root `sam3_vit_h.zip` is the unchanged ONNX conversion from
[vietanhdev/segment-anything-3-onnx-models](https://huggingface.co/vietanhdev/segment-anything-3-onnx-models).
Both retain the [Meta SAM License](LICENSE). The root Transformers files remain a loadable SAM3 snapshot.

## Additional models

| Model | License | Original source |
| --- | --- | --- |
| [chatterbox-turbo](chatterbox-turbo) | [mit](chatterbox-turbo/LICENSE) | [ResembleAI/chatterbox-turbo](https://huggingface.co/ResembleAI/chatterbox-turbo/tree/749d1c1a46eb10492095d68fbcf55691ccf137cd) |
| [madlad-translation](madlad-translation) | [apache-2.0](madlad-translation/LICENSE) | [google/madlad400-3b-mt](https://huggingface.co/google/madlad400-3b-mt/tree/fa184c675da0b5c9e1c8694fccd4e12e2d422094) |
| [qwen-aligner](qwen-aligner) | [apache-2.0](qwen-aligner/LICENSE) | [Qwen/Qwen3-ForcedAligner-0.6B](https://huggingface.co/Qwen/Qwen3-ForcedAligner-0.6B/tree/c7cbfc2048c462b0d63a45797104fc9db3ad62b7) |
| [qwen-asr](qwen-asr) | [apache-2.0](qwen-asr/LICENSE) | [Qwen/Qwen3-ASR-1.7B](https://huggingface.co/Qwen/Qwen3-ASR-1.7B/tree/7278e1e70fe206f11671096ffdd38061171dd6e5) |
| [rnnoise](rnnoise) | [bsd-3-clause](rnnoise/LICENSE) | [https://raw.githubusercontent.com/richardpl/arnndn-models/0fda24c46d78f0207d820bb970fbe85c1971b39c/std.rnnn](https://raw.githubusercontent.com/richardpl/arnndn-models/0fda24c46d78f0207d820bb970fbe85c1971b39c/std.rnnn) |
| [sam2-base-plus](sam2-base-plus) | [apache-2.0](sam2-base-plus/LICENSE) | [facebook/sam2.1-hiera-base-plus](https://huggingface.co/facebook/sam2.1-hiera-base-plus/tree/b7320756a13354e7530a63935656d35b2f91a290) |
| [sam2-large](sam2-large) | [apache-2.0](sam2-large/LICENSE) | [facebook/sam2.1-hiera-large](https://huggingface.co/facebook/sam2.1-hiera-large/tree/665f8e2ad61cf5f53d65644ff27c8ee525124610) |
| [sam2-small](sam2-small) | [apache-2.0](sam2-small/LICENSE) | [facebook/sam2.1-hiera-small](https://huggingface.co/facebook/sam2.1-hiera-small/tree/ee5bba1d82bb8749febdf90f45e84b687142ba03) |
| [sam2-tiny](sam2-tiny) | [apache-2.0](sam2-tiny/LICENSE) | [facebook/sam2.1-hiera-tiny](https://huggingface.co/facebook/sam2.1-hiera-tiny/tree/de431c4043854a71d8101e17995dfe596bf101a5) |
| [tesseract-eng](tesseract-eng) | [apache-2.0](tesseract-eng/LICENSE) | [https://cdn.jsdelivr.net/npm/](https://huggingface.co/https://cdn.jsdelivr.net/npm//tree/tesseract.js-data/eng/4.0.0_best_int/eng.traineddata.gz) |
| [unlimited-ocr](unlimited-ocr) | [mit](unlimited-ocr/LICENSE) | [baidu/Unlimited-OCR](https://huggingface.co/baidu/Unlimited-OCR/tree/8249d20b2822a7d8a4c22c8d8c9069b5ac36bda3) |
| [whisper-large-v3](whisper-large-v3) | [mit](whisper-large-v3/LICENSE) | [Systran/faster-whisper-large-v3](https://huggingface.co/Systran/faster-whisper-large-v3/tree/edaa852ec7e145841d8ffdb056a99866b5f0a478) |
| [whisper-small](whisper-small) | [mit](whisper-small/LICENSE) | [Systran/faster-whisper-small](https://huggingface.co/Systran/faster-whisper-small/tree/536b0662742c02347bc0e980a01041f333bce120) |

| [silero-vad](silero-vad) | [MIT](silero-vad/LICENSE) | [https://pypi.org/project/faster-whisper/1.2.1/](https://pypi.org/project/faster-whisper/1.2.1/) |
| [perth-watermark](perth-watermark) | [MIT](perth-watermark/LICENSE) | [https://pypi.org/project/resemble-perth/1.0.1/](https://pypi.org/project/resemble-perth/1.0.1/) |

Silero VAD and Perth watermarking are unchanged assets bundled with faster-whisper and resemble-perth. SnapTop downloads and verifies these official public files on demand instead of loading the package-bundled copies. Narration setup prepares Perth with Chatterbox; caption speech detection fetches Silero on first use. No provider account or token is required.

MADLAD is used only to generate application translations during development. Qwen ASR/alignment and Unlimited OCR are optional engines.
Software dependencies and runtimes are installed from their official package sources; they are not model payloads in this repository.