From 20160802e2d6026d3193370e487e67ea0e25bf92 Mon Sep 17 00:00:00 2001 From: WongLaw Date: Mon, 13 Feb 2023 08:52:55 +0000 Subject: [PATCH] Cantonese FastSpeech2 Training, test=tts --- examples/canton/tts3/README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/examples/canton/tts3/README.md b/examples/canton/tts3/README.md index fa7d4b64d..1e39a6566 100644 --- a/examples/canton/tts3/README.md +++ b/examples/canton/tts3/README.md @@ -28,6 +28,7 @@ After that, it should be look like: ### Get MFA Result and Extract We use [MFA2.x](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get durations for aishell3_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. +We here provide the MFA results of these two datasets. [canton_mfa_results](https://paddlespeech.bj.bcebos.com/MFA/Canton/canton_alignment.zip) ## Get Started Assume the path to the Cantonese MFA result of the two datsets mentioned above is `./canton_alignment`.