EngineX-Iluvatar/enginex-mr_series-sherpa-onnx
Archived
16
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Use piper-phonemize to convert text to token IDs (#453)

Browse Source
This commit is contained in:
Fangjun Kuang
2023-11-30 23:57:43 +08:00
committed by GitHub
parent db41778e99
commit 62dc3c3e46
55 changed files with 1048 additions and 192 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
nodejs-examples/.gitignore vendored
View File

@@ -1,2 +1,3 @@
node_modules
lib
package-lock.json

7
nodejs-examples/README.md
View File

@@ -42,15 +42,14 @@ In the following, we demonstrate how to run text-to-speech.
## ./test-offline-tts-en.js
[./test-offline-tts-en.js](./test-offline-tts-en.js) shows how to use
a VITS pretrained model
[VCTK](https://k2-fsa.github.io/sherpa/onnx/tts/pretrained_models/vits.html#vctk-english-multi-speaker-109-speakers)
[vits-piper-en_US-amy-low.tar.bz2](https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/vits-piper-en_US-amy-low.tar.bz2)
for text-to-speech.
You can use the following command to run it:
```bash
wget -q https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/vits-vctk.tar.bz2
tar xvf vits-vctk.tar.bz2
wget -q https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/vits-piper-en_US-amy-low.tar.bz2
tar xvf vits-piper-en_US-amy-low.tar.bz2
node ./test-offline-tts-en.js
```

13
nodejs-examples/test-offline-tts-en.js
View File

@@ -4,9 +4,9 @@ const sherpa_onnx = require('sherpa-onnx');
function createOfflineTts() {
const vits = new sherpa_onnx.OfflineTtsVitsModelConfig();
vits.model = './vits-vctk/vits-vctk.onnx';
vits.lexicon = './vits-vctk/lexicon.txt';
vits.tokens = './vits-vctk/tokens.txt';
vits.model = 'vits-piper-en_US-amy-low/en_US-amy-low.onnx'
vits.tokens = './vits-piper-en_US-amy-low/tokens.txt';
vits.dataDir = './vits-piper-en_US-amy-low/espeak-ng-data'
const modelConfig = new sherpa_onnx.OfflineTtsModelConfig();
modelConfig.vits = vits;
@@ -18,10 +18,11 @@ function createOfflineTts() {
}
const tts = createOfflineTts();
const speakerId = 99;
const speakerId = 0;
const speed = 1.0;
const audio =
tts.generate('Good morning. How are you doing?', speakerId, speed);
const audio = tts.generate(
'“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.”',
speakerId, speed);
audio.save('./test-en.wav');
console.log('Saved to test-en.wav successfully.');
tts.free();