From 9761b3094078f00cd5303321c9575a3ae2676684 Mon Sep 17 00:00:00 2001
From: Dapwner <46859435+Dapwner@users.noreply.github.com>
Date: Mon, 3 Jun 2024 14:07:04 +0800
Subject: [PATCH] Update README.md

---
 README.md | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 8154905..1c3be06 100644
--- a/README.md
+++ b/README.md
@@ -1,2 +1,12 @@
 # Accent Conversion in Text-To-Speech Using Multi-Level VAE and Adversarial Training
-This repo combines a Tacotron2 model with a ML-VAE and adversarial learning to target accent conversion in TTS settings (pick a speaker A with and assign them accent B).
\ No newline at end of file
+This repo combines a Tacotron2 model with a ML-VAE and adversarial learning to target accent conversion in TTS settings (pick a speaker A with and assign them accent B).
+Paper link: TBA
+Samples link: https://amaai-lab.github.io/Accented-TTS-MLVAE-ADV/
+
+## Training
+First preprocess your data into mel spectrogram .npy arrays with the preprocess.py script. We used L2CMU in this paper, which stands for a combination of L2Arctic (24 speakers) and CMUArctic (4 speakers). Then run CUDA_VISIBLE_DEVICES=X python train.py --dataset L2CMU
+
+## Inference
+Once trained, you can run extract_stats.py to retrieve the accent and speaker embeddings of your evaluation set and store them. Then, you can synthesize with one of the synth scripts. :-)
+
+Once trained, you can run CUDA_VISIBLE_DEVICES=X python synthesize.py --dataset L2Arctic --restore_step [N] --mode [batch/single] --text [TXT] --speaker_id [SPID] --accent [ACC]