SpeechT5-base-cs-tts

This is a monolingual Czech SpeechT5 base model pre-trained from 120 thousand hours of Czech speech and a large Czech text corpus with 17.5B words. It has been introduced in a paper Zero-Shot vs. Few-Shot Multi-Speaker TTS Using Pre-trained Czech SpeechT5 Model accepted to TSD2024 conference. It is meant to be used as a starting checkpoint for Czech TTS fine-tuning.

Important note: This is only a pre-trained model, so it has not yet been trained for the TTS task.

Examples of fine-tuned voices are available at https://jalehecka.github.io/TSD2024.

See our paper for details.

Paper

https://link.springer.com/chapter/10.1007/978-3-031-70566-3_5

Pre-print: http://arxiv.org/abs/2407.17167.

Citation

If you find this model useful, please cite our paper:

@InProceedings{10.1007/978-3-031-70566-3_5,
  author="Lehe{\v{c}}ka, Jan
    and Hanzl{\'i}{\v{c}}ek, Zden{\v{e}}k
    and Matou{\v{s}}ek, Jind{\v{r}}ich
    and Tihelka, Daniel",
  editor="N{\"o}th, Elmar
    and Hor{\'a}k, Ale{\v{s}}
    and Sojka, Petr",
  title="Zero-Shot vs. Few-Shot Multi-speaker TTS Using Pre-trained Czech SpeechT5 Model",
  booktitle="Text, Speech, and Dialogue",
  year="2024",
  publisher="Springer Nature Switzerland",
  address="Cham",
  pages="46--57",
  isbn="978-3-031-70566-3"
}

Usage

This is a TTS variant of the SpeechT5 model, i.e., the input modality is text (processed via the text pre-net), and the output modality is speech (processed via the speech post-net). The model has the same format as the microsoft/speecht5_tts compatible with the SpeechT5ForTextToSpeech class.

In order to use this model for text-to-speech, it must be fine-tuned on labeled TTS data.

The usage is the same as for the microsoft/speecht5_tts

Related works