auracaster/piper
3
0
Fork 0
mirror of https://github.com/pstrueb/piper.git synced 2026-06-02 09:57:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

More README updates

Browse Source
This commit is contained in:
Michael Hansen
2023-01-10 17:29:58 -06:00
parent b31cece2df
commit 651ddb86a5
1 changed files with 9 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+9 -9
View File
@@ -4,22 +4,22 @@ A fast, local neural text to speech system.
``` sh
echo 'Welcome to the world of speech synthesis!' | \
./larynx --model blizzard_lessac-medium.onnx --output_file welcome.wav
./larynx --model en-us-blizzard_lessac-medium.onnx --output_file welcome.wav
```
## Voices
* [U.S. English](https://github.com/rhasspy/larynx2/releases/download/v0.0.1/voice-english.tar.gz)
* [German](https://github.com/rhasspy/larynx2/releases/download/v0.0.1/voice-german.tar.gz)
* [Danish](https://github.com/rhasspy/larynx2/releases/download/v0.0.1/voice-danish.tar.gz)
* [Norweigian](https://github.com/rhasspy/larynx2/releases/download/v0.0.1/voice-norweigian.tar.gz)
* [Nepali](https://github.com/rhasspy/larynx2/releases/download/v0.0.1/voice-nepali.tar.gz)
* [Vietnamese](https://github.com/rhasspy/larynx2/releases/download/v0.0.1/voice-vietnamese.tar.gz)
* [U.S. English](https://github.com/rhasspy/larynx2/releases/download/v0.0.1/voice-english.tar.gz) (22Khz, single speaker)
* [German](https://github.com/rhasspy/larynx2/releases/download/v0.0.1/voice-german.tar.gz) (16Khz, single speaker)
* [Danish](https://github.com/rhasspy/larynx2/releases/download/v0.0.1/voice-danish.tar.gz) (22Khz, multispeaker)
* [Norweigian](https://github.com/rhasspy/larynx2/releases/download/v0.0.1/voice-norweigian.tar.gz) (22Khz, single speaker)
* [Nepali](https://github.com/rhasspy/larynx2/releases/download/v0.0.1/voice-nepali.tar.gz) (16Khz, multispeaker)
* [Vietnamese](https://github.com/rhasspy/larynx2/releases/download/v0.0.1/voice-vietnamese.tar.gz) (16Khz, multispeaker)
## Purpose
Larynx is meant to sound as good as [CoquiTTS](https://github.com/coqui-ai/TTS), but run reasonbly fast on the Raspberry Pi 4.
Larynx is meant to sound as good as [CoquiTTS](https://github.com/coqui-ai/TTS), but run reasonably fast on the Raspberry Pi 4.
Voices are trained with [VITS](https://github.com/jaywalnut310/vits/) and exported to the [onnxruntime](https://onnxruntime.ai/).
@@ -37,7 +37,7 @@ If you want to build from source, see the [Makefile](Makefile) and [C++ source](
## Usage
1. [Download a voice](#voices) and extract the `.onnx` and `.onnx.json` files
2. Run the `larynx` binary with text on stdin, `--model /path/to/your-voice.onnx`, and `--output_file output.wav`
2. Run the `larynx` binary with text on standard input, `--model /path/to/your-voice.onnx`, and `--output_file output.wav`
For example: