From 2f42c69d25a2bea72becfe8c51f6a36defb1ba41 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Thu, 18 Apr 2024 15:57:32 +0100
Subject: [PATCH] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 92332a4..e523432 100644
--- a/README.md
+++ b/README.md
@@ -995,7 +995,7 @@ If you wish to try out the XTTS version 2.0.3 model and see if it works better,
 ### ⚫ Finetuning a model
 If you have a voice that the model doesnt quite reproduce correctly, or indeed you just want to improve the reproduced voice, then finetuning is a way to train your "XTTSv2 local" model **(stored in `/alltalk_tts/models/xxxxx/`)** on a specific voice. For this you will need:
 
-- An Nvidia graphics card. (Please see the help section [note](https://github.com/erew123/alltalk_tts/edit/main/README.md#performance-and-compatibility-issues) if you have multiple Nvidia GPU's).
+- An Nvidia graphics card. (Please see the help section [note](https://github.com/erew123/alltalk_tts/edit/main/README.md#performance-and-compatibility-issues) if you have multiple Nvidia GPU's). Preferably 12GB+ VRAM on Windows. Minimum 16GB VRAM on Linux.
 - 18GB of disk space free (most of this is used temporarily)
 - At least 2 minutes of good quality speech from your chosen speaker in mp3, wav or flacc format, in one or more files (have tested as far as 20 minutes worth of audio).
 - As a side note, many people seem to think that the Whisper v2 model (used on Step 1) is giving better results at generating training datasets, so you may prefer to try that, as opposed to the Whisper 3 model.