First commit

README.md

@@ -0,0 +1,23 @@
+---
+license: apache-2.0
+base_model:
+- ResembleAI/chatterbox
+---
+
+
+This model is a VC-only (voice conversion) extract for MLX Chatterbox.
+
+This model was converted to MLX format from [ResembleAI/chatterbox](https://huggingface.co/ResembleAI/chatterbox) using [mlx-audio](https://github.com/Blaizzy/mlx-audio) version **0.2.10**.
+
+What’s inside
+
+s3gen.safetensors: token→audio decoder (S3Gen)
+ve.safetensors: voice encoder weights (not required for the minimal VC script below, but included for completeness)
+Optional conds.safetensors / config.json if you included them
+Use with MLX (VC / audio→audio)
+
+Install
+
+```bash
+pip install -U mlx-audio`
+```

conds.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:709e5a7fa80e010a011c8244f553853aed7a49c106fff54008fbd89a0f5a6148
+size 105316

config.json

@@ -0,0 +1,7 @@
+{
+  "model_type": "chatterbox",
+  "version": "1.0",
+  "multilingual": true,
+  "vocab_size": 2454,
+  "precision": "fp16"
+}

s3gen.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b01b6939abfc557a092c0ce902b628b9ad12bd342a57b1879043e1c7db1dcdb
+size 424792228

ve.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a35421e72bf35f91a8a45ae0a70ec88d126e68cd79dd89c472834e63d1ea4569
+size 5683320