Upload folder using huggingface_hub

README.md

@@ -0,0 +1,20 @@
+---
+license: cc-by-nc-sa-4.0
+tags:
+- audio
+- codec
+- autoencoder
+- pytorch
+---
+
+# Fish-Speech S1 DAC Autoencoder weights (redistribution)
+
+An **unofficial** redistribution / mirror of the Fish-S1 DAC autoencoder weights, licensed **CC BY-NC-SA 4.0**.
+
+### Attribution:
+- **Original project:** [Fish-Speech](https://github.com/fishaudio/fish-speech) (Fish Audio).
+- **Original model release:** [fishaudio/openaudio-s1-mini](https://huggingface.co/fishaudio/openaudio-s1-mini).
+- **License (weights):** **CC BY‑NC‑SA 4.0** — non‑commercial use, attribution required, ShareAlike.  
+  See: https://creativecommons.org/licenses/by-nc-sa/4.0/
+- **Changes in this mirror:** converted to `.safetensors` and repackaged with a minimal `config.json` for convenience; no training/content changes.
+- **Status:** Unofficial redistribution/mirror; not affiliated with or endorsed by the original authors. The license and non‑commercial terms are preserved.

config.json

@@ -0,0 +1,24 @@
+{
+  "sample_rate": 44100,
+  "encoder_dim": 64,
+  "encoder_rates": [
+    2,
+    4,
+    8,
+    8
+  ],
+  "latent_dim": 1024,
+  "decoder_dim": 1536,
+  "decoder_rates": [
+    8,
+    8,
+    4,
+    2
+  ],
+  "n_codebooks": 9,
+  "codebook_size": 1024,
+  "codebook_dim": 8,
+  "semantic_codebook_size": 4096,
+  "quantizer_dropout": 0.5,
+  "causal": true
+}

pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50abb71421977290a1b7eaf1e88c1048824c1fab28d1839c59f97b0fe7616e11
+size 1870925072