# Provenance — vokra/frcrn

| Field | Value |
|---|---|
| Upstream source | alibabasglab/FRCRN (Complex U-Net + frequency-recurrent LSTM, DNS Challenge 2022, apache-2.0; also distributed via modelscope/ClearerVoice-Studio) |
| Upstream licence | `apache-2.0` |
| Architecture | `frcrn` |
| Tensors | 812 |
| SHA-256 | `04b8810e3f9e6391d9b95158fc34a2050bcac8618a3b25deb534a1b9cd42d7b6` |
| Converted by | vokra-core 0.1.0-alpha.0 |
| GGUF schema generation | 1 |

Every row is read from the artifact's own `vokra.*` metadata; none of it
is supplied by hand, so this file cannot disagree with the weight it
describes.

## Reproducing

```bash
vokra-cli convert --model <kind> --input <upstream> --output frcrn.gguf
shasum -a 256 frcrn.gguf   # expect 04b8810e3f9e6391d9b95158fc34a2050bcac8618a3b25deb534a1b9cd42d7b6
```