phoonnx_an_miro_unicode

phoonnx_an_miro_unicode

This is a text-to-speech voice model for Aragonese. The voice is Miro, a male voice. It uses the phoonnx VITS architecture with a unicode character-based phonemizer, exported to ONNX for CPU inference. It was fine-tuned from the base voice phoonnx_ast_miro_unicode, the closest available language for this voice.

How to use

Install phoonnx and run:

import wave
from phoonnx.config import SynthesisConfig
from phoonnx.voice import TTSVoice

voice = TTSVoice.from_hf("OpenVoiceOS/phoonnx_an_miro_unicode")

synthesis_config = SynthesisConfig(noise_scale=0.667, length_scale=1.0, noise_w_scale=0.8)

with wave.open("output.wav", "wb") as wav_file:
    voice.synthesize_wav("Buenas días, ¿cómo estás?", wav_file, synthesis_config)

You can also use this model in OVOS with ovos-tts-plugin-phoonnx:

{
  "tts": {
    "module": "ovos-tts-plugin-phoonnx",
    "ovos-tts-plugin-phoonnx": {
      "voice": "OpenVoiceOS/phoonnx_an_miro_unicode"
    }
  }
}

Training data

Trained on TigreGotico/tts_vc_mcv-scripted-v23.0_an_miro.

Related links

• Training-data collection: https://huggingface.co/collections/TigreGotico/synthetic-tts-datasets
• phoonnx: https://github.com/TigreGotico/phoonnx
• voiceclonnx: https://github.com/TigreGotico/voiceclonnx
• TigreGotico: https://tigregotico.pt

Ownership and licensing

Miro and Dii are the recorded voices of two real people. The voices, the training data, and this model belong to TigreGotico Lda (https://tigregotico.pt).

This model is licensed under Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 (CC BY-NC-ND 4.0). You may use and share this model for non-commercial purposes only. Give attribution to TigreGotico Lda. Do not modify, adapt, or build new models from this model. Do not use the voice identity to create derivative voices.

For commercial use, for derivative models, or for any other license of the Miro or Dii voice identity, contact TigreGotico Lda.

The training checkpoint is kept out of this repository so a download is the model and not the training state. It is available on request.