test1 — Piper TTS voice
A Piper text-to-speech voice fine-tuned with TiengNoi Studio.
| Voice name | test1 |
| Language (espeak-ng) | vi |
| Sample rate | 22050 Hz (medium quality) |
| Base checkpoint | en_US/hfc_male/medium |
| Training dataset | JayLL13/dataset-test-1 |
| Max epochs | 2 |
Files
test1.onnx— the exported voice model.test1.onnx.json— the voice config (phonemes, sample rate, inference defaults).
Usage
pip install piper-tts
python -m piper --model test1.onnx --output-file out.wav <<< "Xin chào"
import wave
from piper import PiperVoice, SynthesisConfig
voice = PiperVoice.load("test1.onnx", config_path="test1.onnx.json")
with wave.open("out.wav", "wb") as wav:
voice.synthesize_wav("Xin chào tất cả mọi người", wav, syn_config=SynthesisConfig())
Generated by TiengNoi Studio (flow 2: fine-tune).
- Downloads last month
- -
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js