TorToise

This is a mirror of the original weights for use with TTSDB.

Original weights: https://huggingface.co/jbetker/tortoise-tts-v2 Original code: https://github.com/neonbjb/tortoise-tts.git

Tortoise TTS voice cloning model.

Original Work

This model was created by the original authors. Please cite their work if you use this model:

@misc{betker2023betterspeechsynthesisscaling,
  title={Better speech synthesis through scaling},
  author={James Betker},
  year={2023},
  eprint={2305.07243},
  archivePrefix={arXiv},
  primaryClass={cs.SD},
  url={https://arxiv.org/abs/2305.07243},
}

Papers:

• https://arxiv.org/abs/2305.07243

Installation

pip install ttsdb-tortoise

Usage

from ttsdb_tortoise import TorToise

# Load the model (downloads weights automatically)
model = TorToise(model_id="ttsds/TorToise")

# Synthesize speech
audio, sample_rate = model.synthesize(
    text="Hello, this is a test of TorToise.",
    reference_audio="path/to/reference.wav",
    text_reference="Transcript of the reference audio.",
    language="en",
)

# Save the output
model.save_audio(audio, sample_rate, "output.wav")

Model Details

Property	Value
Sample Rate	24000 Hz
Parameters	960M
Architecture	Autoregressive, Diffusion, Language Modeling
Languages	English
Release Date	2022-05-17

Training Data

• LibriTTS

• HifiTTS

License

• Weights: Other (see original repository)
• Code: Apache License 2.0

Please refer to the original repositories for full license terms.

Links

• Original Code: https://github.com/neonbjb/tortoise-tts.git
• Original Weights: https://huggingface.co/jbetker/tortoise-tts-v2
• TTSDB Package: ttsdb-tortoise
• TTSDB GitHub: https://github.com/ttsds/ttsdb