EngineX-Iluvatar/enginex-mr_series-sherpa-onnx
Archived
15
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Support Matcha-TTS models using espeak-ng (#1672)

Browse Source
This commit is contained in:
Fangjun Kuang
2025-01-02 13:46:43 +08:00
committed by GitHub
parent 3422b9388d
commit f457baea42
10 changed files with 290 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
.github/scripts/test-python.sh vendored
View File

@@ -267,7 +267,27 @@ log "Offline TTS test"
# test waves are saved in ./tts
mkdir ./tts
log "vits-ljs test"
log "matcha-ljspeech-en test"
curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/matcha-icefall-en_US-ljspeech.tar.bz2
tar xvf matcha-icefall-en_US-ljspeech.tar.bz2
rm matcha-icefall-en_US-ljspeech.tar.bz2
curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/vocoder-models/hifigan_v2.onnx
python3 ./python-api-examples/offline-tts.py \
--matcha-acoustic-model=./matcha-icefall-en_US-ljspeech/model-steps-3.onnx \
--matcha-vocoder=./hifigan_v2.onnx \
--matcha-tokens=./matcha-icefall-en_US-ljspeech/tokens.txt \
--matcha-data-dir=./matcha-icefall-en_US-ljspeech/espeak-ng-data \
--output-filename=./tts/test-matcha-ljspeech-en.wav \
--num-threads=2 \
"Today as always, men fall into two groups: slaves and free men. Whoever does not have two-thirds of his day for himself, is a slave, whatever he may be: a statesman, a businessman, an official, or a scholar."
rm hifigan_v2.onnx
rm -rf matcha-icefall-en_US-ljspeech
log "matcha-baker-zh test"
curl -O -SL https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/matcha-icefall-zh-baker.tar.bz2
tar xvf matcha-icefall-zh-baker.tar.bz2
@@ -282,12 +302,13 @@ python3 ./python-api-examples/offline-tts.py \
--matcha-tokens=./matcha-icefall-zh-baker/tokens.txt \
--tts-rule-fsts=./matcha-icefall-zh-baker/phone.fst,./matcha-icefall-zh-baker/date.fst,./matcha-icefall-zh-baker/number.fst \
--matcha-dict-dir=./matcha-icefall-zh-baker/dict \
--output-filename=./tts/test-matcha.wav \
--output-filename=./tts/test-matcha-baker-zh.wav \
"某某银行的副行长和一些行政领导表示，他们去过长江和长白山; 经济不断增长。2024年12月31号，拨打110或者18920240511。123456块钱。"
rm -rf matcha-icefall-zh-baker
rm hifigan_v2.onnx
log "vits-ljs test"
curl -LS -O https://huggingface.co/csukuangfj/vits-ljs/resolve/main/vits-ljs.onnx
curl -LS -O https://huggingface.co/csukuangfj/vits-ljs/resolve/main/lexicon.txt