From 43eabf21da367a9e29167dbfbffe89012de92509 Mon Sep 17 00:00:00 2001
From: RVC-Boss <129054828+RVC-Boss@users.noreply.github.com>
Date: Tue, 11 Feb 2025 21:08:33 +0800
Subject: [PATCH] gpt_sovits_v3

gpt_sovits_v3
---
 GPT_SoVITS/f5_tts/model/backbones/README.md | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)
 create mode 100644 GPT_SoVITS/f5_tts/model/backbones/README.md

diff --git a/GPT_SoVITS/f5_tts/model/backbones/README.md b/GPT_SoVITS/f5_tts/model/backbones/README.md
new file mode 100644
index 0000000..155671e
--- /dev/null
+++ b/GPT_SoVITS/f5_tts/model/backbones/README.md
@@ -0,0 +1,20 @@
+## Backbones quick introduction
+
+
+### unett.py
+- flat unet transformer
+- structure same as in e2-tts & voicebox paper except using rotary pos emb
+- update: allow possible abs pos emb & convnextv2 blocks for embedded text before concat
+
+### dit.py
+- adaln-zero dit
+- embedded timestep as condition
+- concatted noised_input + masked_cond + embedded_text, linear proj in
+- possible abs pos emb & convnextv2 blocks for embedded text before concat
+- possible long skip connection (first layer to last layer)
+
+### mmdit.py
+- sd3 structure
+- timestep as condition
+- left stream: text embedded and applied a abs pos emb
+- right stream: masked_cond & noised_input concatted and with same conv pos emb as unett