Download Latest Version tts_models--en--ljspeech--tacotron2-DCA.zip (312.6 MB)
Email in envelope

Get an email when there's a new version of TTS

Home / v0.0.9
Name Modified Size InfoDownloads / Week
Parent folder
vocoder_models--universal--libri-tts--wavegrad.zip 2021-01-29 174.9 MB
vocoder_models--universal--libri-tts--fullband-melgan.zip 2021-01-29 76.7 MB
vocoder_models--en--ljspeech--mulitband-melgan.zip 2021-01-29 76.7 MB
tts_models--fr--mai--tacotron2-DDC.zip 2021-01-29 524.3 MB
tts_models--es--mai--tacotron2-DDC.zip 2021-01-29 523.2 MB
tts_models--en--ljspeech--tacotron2-DCA.zip 2021-01-29 312.6 MB
tts_models--en--ljspeech--glow-tts.zip 2021-01-29 315.1 MB
README.md 2021-01-27 2.0 kB
TTS v0.0.9 (first release).tar.gz 2021-01-27 14.8 MB
TTS v0.0.9 (first release).zip 2021-01-27 14.9 MB
Totals: 10 Items   2.0 GB 6

This is the first and v0.0.9 release of TTS, an open text-to-speech engine. TTS is still an evolving project and any upcoming release might be significantly different and not backward compatible.

In this release, we provide the following models.

Language Dataset Model Name Model Type Download
English LJSpeech TacotronDCA tts 💾
English LJSpeech Glow-TTS tts 💾
Spanish M-AILabs TacotronDDC tts 💾
French M_AILabs TacotronDDC tts 💾
English LJSpeech MB-MelGAN vocoder 💾
Multi-Lang LibriTTS FullBand-MelGAN vocoder 💾
Multi-Lang LibriTTS WaveGrad vocoder 💾

Notes

  • Multi-Lang vocoder models are intended for non-English models.
  • Vocoder models are independently trained from the tts models with possibly different sampling rates. Therefore, the performance is not optimal.
  • All models are trained with phonemes generated by espeak back-end (not espeak-ng).

This release has been tested under Python 3.6, 3.7, and 3.8. It is strongly suggested to use conda to install the dependencies and set-up the runtime environment.

Source: README.md, updated 2021-01-27