JayLL13/piper-voice-test-1

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).