desert-ant-labs-source-available-1.0
Fonte do modelo
Trecho da fonte
desert-ant-labs-source-available-1.0
Fontes
1 fonteVerificado 2 de ago.
Artefatos de modelo
10 artefatosTrechos de fonte
2 trechosclear-natural.mlmodelc/weights/weight.bin
bin · 8,86 MB · SHA-256 d43736ffb7eb…571b · Hugging Face
clear-studio.mlmodelc/analytics/coremldata.bin
bin · 243 B · SHA-256 5e33873685fe…51f9 · Hugging Face
Baixarclear-studio.mlmodelc/weights/weight.bin
bin · 8,86 MB · SHA-256 5929f42180be…9943 · Hugging Face
Baixar--- license: other license_name: desert-ant-labs-source-available-1.0 license_link: https://license.desertant.com/1.0 language: - en tags: - audio - speech-enhancement - denoising - dereverberation - on-device - core-ml - onnx pipeline_tag: audio-to-audio --- # Clear: on-device speech enhancement 48 kHz on-device speech enhancement. Takes noisy mono or stereo audio (phone mic, untreated room, traffic), returns a podcast-ready file: denoised, dereverbed, voice warm and present. ## Try it - **Live demo:** [desert-ant-labs/clear-demo](https://huggingface.co/spaces/desert-ant-labs/clear-demo): drop in a recording and hear raw vs cleaned, fully in your browser. - **iOS / macOS:** [`clear-swift`](https://github.com/Desert-Ant-Labs/clear-swift): Swift package; both variants bundled, works offline. - **Android / JVM:** [`clear-kotlin`](https://github.com/Desert-Ant-Labs/clear-kotlin): Kotlin SDK via JitPack. - **JavaScript / TypeScript:** [`@desert-ant-labs/clear`](https://www.npmjs.com/package/@desert-ant-labs/clear): npm package for Node + browser ([source](https://github.com/Desert-Ant-Labs/clear-js)). For commercial licensing above 100k MAU, email <licensing@desertant.com>. ## Variants | Variant | Character | When to use | |---|---|---| | **`clear-studio`** | Quiet, studio-like; silences near zero | Default. Works across the full range of input quality: phone audio, laptop mic, untreated rooms, USB / XLR podcast captures. | | **`clear-natural`** | Room tone, breath, lip texture preserved | Treated podcast studios, USB / XLR captures, voiceover where the original sound is intentional. | If the source is already clean and you want the model to stay invisible, pick `clear-natural`. Otherwise `clear-studio` is the default. ## Files Both variants share the same architecture and realtime cost; only the weights differ. Both variants are **6-bit palettized** (k-means LUT), ~5× smaller than the fp32 weights with no perceptible quality loss (DNSMOS OVRL within ~0.02 of the float model). | Variant | File | Format | Size | |---|---|---|---:| | `clear-studio` | `clear-studio.mlmodelc/` | Core ML, 6-bit palettized, precompiled | ~1.9 MB | | `clear-studio` | `clear-studio.onnx` | ONNX, 6-bit palettized (fp16-stored) | ~4.5 MB | | `clear-natural` | `clear-natural.mlmodelc/` | Core ML, 6-bit palettized, precompiled | ~1.9 MB | | `clear-natural` | `clear-natural.on...
Source context: 0 downloads · 12 likes · Pipeline audio-to-audio · Repo desert-ant-labs/clear