From d3e86b3fbf748c98c2e557a23002e5cacdfc106a Mon Sep 17 00:00:00 2001
From: Akmal <72781956+Wikidepia@users.noreply.github.com>
Date: Sat, 6 Aug 2022 17:11:34 +0700
Subject: [PATCH] Update README.md

---
 README.md | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 6299d69..71e15c9 100644
--- a/README.md
+++ b/README.md
@@ -2,7 +2,7 @@
 
 Indonesian TTS using Coqui TTS. Models are available in [Releases](https://github.com/Wikidepia/indonesian-tts/releases/) tab.
 
-**DO NOT USE FOR COMMERCIAL PURPOSES.**
+**DO NOT USE FOR COMMERCIAL PURPOSES!**
 
 ## Model changelog
 
@@ -29,10 +29,24 @@ https://user-images.githubusercontent.com/72781956/183240414-b1127e83-6ddd-427c-
 
 https://user-images.githubusercontent.com/72781956/183240420-a5d0d335-af4a-4563-a744-40f6795955c5.mp4
 
-`Semar (Audiobook)`:
+`Wibowo (Audiobook)`:
 
 https://user-images.githubusercontent.com/72781956/183240434-fb0c3656-8673-453e-8900-f4df491e0d0b.mp4
 
+## How to use
+
+You need [`g2p-id`](https://github.com/Wikidepia/g2p-id) to convert grapheme to phoneme. 
+
+Use `tts` command from Coqui TTS to synthesize speech:
+
+```
+tts --text "saja səˈdanʔ ˈbərada di dʒaˈkarta." \
+    --model_path checkpoint.pth \
+    --config_path config.json \
+    --speaker_idx wibowo \
+    --out_path output.wav
+```
+
 ## Data
 
 - [Indonesian Azure TTS](https://depia.wiki/files/azure-tts.tar)