Instructions to use Avdpro/MLX-RVC-Serena-E70 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Avdpro/MLX-RVC-Serena-E70 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download Avdpro/MLX-RVC-Serena-E70 --local-dir MLX-RVC-Serena-E70
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Add native MLX RVC voice-training initialization
Browse files- NOTICE.md +2 -0
- README.md +5 -4
- ai2apps-checkpoint.json +21 -5
- training/discriminator.safetensors +3 -0
- training/generator.safetensors +3 -0
- training/manifest.json +32 -0
NOTICE.md
CHANGED
|
@@ -6,5 +6,7 @@
|
|
| 6 |
- The bundled functional voice is trained from synthetic audio generated with
|
| 7 |
the Qwen3-TTS `serena` preset. It is marked as synthetic in the checkpoint
|
| 8 |
manifest and must not be represented as a recording of a real person.
|
|
|
|
|
|
|
| 9 |
- The Package performs local voice conversion only. It does not grant rights
|
| 10 |
to source recordings supplied by a user.
|
|
|
|
| 6 |
- The bundled functional voice is trained from synthetic audio generated with
|
| 7 |
the Qwen3-TTS `serena` preset. It is marked as synthetic in the checkpoint
|
| 8 |
manifest and must not be represented as a recording of a real person.
|
| 9 |
+
- The native MLX training initialization is a safetensors conversion of the
|
| 10 |
+
pinned upstream RVC v2/48 kHz generator and discriminator checkpoints.
|
| 11 |
- The Package performs local voice conversion only. It does not grant rights
|
| 12 |
to source recordings supplied by a user.
|
README.md
CHANGED
|
@@ -10,10 +10,11 @@ tags:
|
|
| 10 |
# MLX-RVC Serena e70
|
| 11 |
|
| 12 |
Native MLX RVC v2/48 kHz composite checkpoint for AI2Apps. It contains the
|
| 13 |
-
MLX-trained e70 synthetic Serena test voice, its exact retrieval index,
|
| 14 |
-
shared ContentVec and RMVPE
|
| 15 |
-
|
| 16 |
-
|
|
|
|
| 17 |
|
| 18 |
The voice training corpus was generated with the `serena` preset of Qwen3-TTS
|
| 19 |
and is intended as a built-in functional voice, not as the identity of a real
|
|
|
|
| 10 |
# MLX-RVC Serena e70
|
| 11 |
|
| 12 |
Native MLX RVC v2/48 kHz composite checkpoint for AI2Apps. It contains the
|
| 13 |
+
MLX-trained e70 synthetic Serena test voice, its exact retrieval index, the
|
| 14 |
+
shared ContentVec and RMVPE components, and the converted RVC v2/48 kHz
|
| 15 |
+
generator/discriminator initialization used by the native MLX trainer. The
|
| 16 |
+
checkpoint contains only safetensors and JSON; it does not require Torch,
|
| 17 |
+
torchaudio, FAISS, or pickle at runtime.
|
| 18 |
|
| 19 |
The voice training corpus was generated with the `serena` preset of Qwen3-TTS
|
| 20 |
and is intended as a built-in functional voice, not as the identity of a real
|
ai2apps-checkpoint.json
CHANGED
|
@@ -6,7 +6,8 @@
|
|
| 6 |
"components": {
|
| 7 |
"voice": "voice",
|
| 8 |
"contentvec": "contentvec",
|
| 9 |
-
"rmvpe": "rmvpe"
|
|
|
|
| 10 |
},
|
| 11 |
"files": [
|
| 12 |
{
|
|
@@ -59,15 +60,30 @@
|
|
| 59 |
"size": 441,
|
| 60 |
"sha256": "c5087cfb5ed6395e6e151f639cc87eb6bad0994bf06c71d7b765ed83690f5b14"
|
| 61 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
{
|
| 63 |
"path": "README.md",
|
| 64 |
-
"size":
|
| 65 |
-
"sha256": "
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"path": "NOTICE.md",
|
| 69 |
-
"size":
|
| 70 |
-
"sha256": "
|
| 71 |
},
|
| 72 |
{
|
| 73 |
"path": "LICENSE",
|
|
|
|
| 6 |
"components": {
|
| 7 |
"voice": "voice",
|
| 8 |
"contentvec": "contentvec",
|
| 9 |
+
"rmvpe": "rmvpe",
|
| 10 |
+
"training": "training"
|
| 11 |
},
|
| 12 |
"files": [
|
| 13 |
{
|
|
|
|
| 60 |
"size": 441,
|
| 61 |
"sha256": "c5087cfb5ed6395e6e151f639cc87eb6bad0994bf06c71d7b765ed83690f5b14"
|
| 62 |
},
|
| 63 |
+
{
|
| 64 |
+
"path": "training/generator.safetensors",
|
| 65 |
+
"size": 150433888,
|
| 66 |
+
"sha256": "d2979ac5acf184ead3b5c62232d083e72ba7592441509ca88f6a496acca00573"
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"path": "training/discriminator.safetensors",
|
| 70 |
+
"size": 285553012,
|
| 71 |
+
"sha256": "6672bcb014b6b8d1ba87f9bf9caffc4c1cb6f73375184ce4156d13c13437441c"
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"path": "training/manifest.json",
|
| 75 |
+
"size": 905,
|
| 76 |
+
"sha256": "6d3ecfc37a9f8da68577d3a8f1d6b77c90da2497d2be52d2845a1287469ff916"
|
| 77 |
+
},
|
| 78 |
{
|
| 79 |
"path": "README.md",
|
| 80 |
+
"size": 970,
|
| 81 |
+
"sha256": "e5cd710ab7ac2329fa200cb57b310ccd3e2d6081284085ff977b46ac7444b1af"
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"path": "NOTICE.md",
|
| 85 |
+
"size": 670,
|
| 86 |
+
"sha256": "1520786160efa529c76e1d614e97f4d22d02af184fc073466f394b290eb0d5fe"
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"path": "LICENSE",
|
training/discriminator.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6672bcb014b6b8d1ba87f9bf9caffc4c1cb6f73375184ce4156d13c13437441c
|
| 3 |
+
size 285553012
|
training/generator.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2979ac5acf184ead3b5c62232d083e72ba7592441509ca88f6a496acca00573
|
| 3 |
+
size 150433888
|
training/manifest.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema": "ai2apps.mlx-rvc-training-checkpoint/v1",
|
| 3 |
+
"version": "v2",
|
| 4 |
+
"sample_rate": 48000,
|
| 5 |
+
"uses_f0": true,
|
| 6 |
+
"generator": {
|
| 7 |
+
"source": {
|
| 8 |
+
"name": "f0G48k.pth",
|
| 9 |
+
"sha256": "b5d51f589cc3632d4eae36a315b4179397695042edc01d15312e1bddc2b764a4"
|
| 10 |
+
},
|
| 11 |
+
"weights": {
|
| 12 |
+
"name": "generator.safetensors",
|
| 13 |
+
"sha256": "d2979ac5acf184ead3b5c62232d083e72ba7592441509ca88f6a496acca00573",
|
| 14 |
+
"tensor_count": 423,
|
| 15 |
+
"parameter_count": 37597570,
|
| 16 |
+
"dtype": "float32"
|
| 17 |
+
}
|
| 18 |
+
},
|
| 19 |
+
"discriminator": {
|
| 20 |
+
"source": {
|
| 21 |
+
"name": "f0D48k.pth",
|
| 22 |
+
"sha256": "2269b73c7a4cf34da09aea99274dabf99b2ddb8a42cbfb065fb3c0aa9a2fc748"
|
| 23 |
+
},
|
| 24 |
+
"weights": {
|
| 25 |
+
"name": "discriminator.safetensors",
|
| 26 |
+
"sha256": "6672bcb014b6b8d1ba87f9bf9caffc4c1cb6f73375184ce4156d13c13437441c",
|
| 27 |
+
"tensor_count": 110,
|
| 28 |
+
"parameter_count": 71385417,
|
| 29 |
+
"dtype": "float32"
|
| 30 |
+
}
|
| 31 |
+
}
|
| 32 |
+
}
|