From 22f8a0971ca0eecbbdd132dbdad85e7eae47ef20 Mon Sep 17 00:00:00 2001
From: WongLaw <mailoflawrence@gmail.com>
Date: Mon, 13 Feb 2023 11:50:01 +0000
Subject: [PATCH] Cantonese FastSpeech2 Training, test=tts

---
 examples/canton/tts3/README.md | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/examples/canton/tts3/README.md b/examples/canton/tts3/README.md
index 35115f659..a4e7a5b96 100644
--- a/examples/canton/tts3/README.md
+++ b/examples/canton/tts3/README.md
@@ -14,15 +14,17 @@ cp -r ~/datasets/Guangzhou_Cantonese_Scripted_Speech_Corpus_in_Vehicle/WAV/* ~/d
 
 After that, it should be look like:
 `
-~/datasets/canton_all_
+```~/datasets/canton_all_
 │   └── WAV
 │       └──G0001
 │       └──G0002
 │       ...
 │       └──G0071
 │       └──G0072
+```
 `
- 
+
+
 ### Get MFA Result and Extract
 We use [MFA1.x](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get durations for canton_fastspeech2.
 You can train your MFA model reference to [canton_mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.