From 28dc83f63a3d16816a86095388b68688bccab027 Mon Sep 17 00:00:00 2001 From: WongLaw Date: Wed, 8 Feb 2023 12:22:34 +0000 Subject: [PATCH] Cantonese TTS MFA pipeline, test=tts --- examples/other/mfa/README.md | 7 +++++++ examples/other/mfa/run_canton.sh | 2 +- 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/examples/other/mfa/README.md b/examples/other/mfa/README.md index 216d1275b..88054019b 100644 --- a/examples/other/mfa/README.md +++ b/examples/other/mfa/README.md @@ -7,3 +7,10 @@ Run the following script to get started, for more detail, please see `run.sh`. # Rhythm tags for MFA If you want to get rhythm tags with duration through MFA tool, you may add flag `--rhy-with-duration` in the first two commands in `run.sh` Note that only CSMSC dataset is supported so far, and we replace `#` with `sp` in rhythm tags for MFA. + +# MFA for Cantonese language +First, go download these datasets [Guangzhou_Cantonese_Scripted_Speech_Corpus_Daily_Use_Sentence](https://paddlespeech.bj.bcebos.com/datasets/Cantonese/Guangzhou_Cantonese_Scripted_Speech_Corpus_Daily_Use_Sentence.zip) and [Guangzhou_Cantonese_Scripted_Speech_Corpus_in_Vehicle](https://paddlespeech.bj.bcebos.com/datasets/Cantonese/Guangzhou_Cantonese_Scripted_Speech_Corpus_in_Vehicle.zip) under `~/dataset/`. +Then, +```bash +./run_canton.sh +``` diff --git a/examples/other/mfa/run_canton.sh b/examples/other/mfa/run_canton.sh index 79bf3387f..69c113276 100755 --- a/examples/other/mfa/run_canton.sh +++ b/examples/other/mfa/run_canton.sh @@ -4,7 +4,7 @@ mkdir -p $EXP_DIR LEXICON_NAME='canton' if [ ! -f "$EXP_DIR/$LEXICON_NAME.lexicon" ]; then echo "generating lexicon and training data..." - python local/generate_canton_lexicon_wavlabs.py --output_lexicon "$EXP_DIR/$LEXICON_NAME.lexicon" --output_wavlabs "$EXP_DIR/$LEXICON_NAME"_wavlabs --inputs Guangzhou_Cantonese_Scripted_Speech_Corpus_Daily_Use_Sentence Guangzhou_Cantonese_Scripted_Speech_Corpus_in_Vehicle + python local/generate_canton_lexicon_wavlabs.py --output_lexicon "$EXP_DIR/$LEXICON_NAME.lexicon" --output_wavlabs "$EXP_DIR/$LEXICON_NAME"_wavlabs --inputs ~/dataset/Guangzhou_Cantonese_Scripted_Speech_Corpus_Daily_Use_Sentence ~/dataset/Guangzhou_Cantonese_Scripted_Speech_Corpus_in_Vehicle echo "lexicon and training data done" fi