Upload 4 files

.gitattributes

@@ -0,0 +1,2 @@
+ResNet293_SimAM_ASP_base_LDA-128.pt filter=lfs diff=lfs merge=lfs -text
+ResNet293_SimAM_ASP_base.pt filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,8 @@
+---
+license: apache-2.0
+---
+This repository contains the speaker embedding models for our Zonos-v0.1 [transformer](https://huggingface.co/Zyphra/Zonos-v0.1-transformer) and [hybrid](https://huggingface.co/Zyphra/Zonos-v0.1-hybrid) models.
+
+The speaker embedding models are based on the [ResNet293-SimAM-ASP](https://github.com/VoxBlink2/ScriptsForVoxBlink2/tree/main/asv) models from VoxBlink2. We use the pretrain models as we found the finetunes performed worse.
+
+The output of the speaker embedding model is then passed through an LDA layer and compressed from 256 to 128 dimensions to remove further spurious information about the speaker embedding clip before being fed into the Zonos models.

ResNet293_SimAM_ASP_base.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f02677cd204f91e228f9ec344b7262749a9ab80b9848a7e0452e198d629a65d
+size 396513742

ResNet293_SimAM_ASP_base_LDA-128.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:383d4289dacaeac44386716ef15f7a1de6ff069d2a07ec1e933526eef5bd0084
+size 264512

gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text