There is a newer version of the record available.

Published September 13, 2021 | Version v0.3.0
Software Open

coqui-ai/TTS: v0.3.0

Authors/Creators

  • 1. Coqui.ai
  • 2. University of São Paulo (USP)
  • 3. Faculty of Electrical Engineering and Information Technologies
  • 4. University of Münster (WWU)
  • 5. no

Description

🐸 v0.3.0 New ForwardTTS implementation.

This version implements a new ForwardTTS interface that can be configured as any feed-forward TTS model that uses a duration predictor at inference time. Currently, we provide 3 pre-configured models and plan to implement one more.

  1. SpeedySpeech
  2. FastSpeech
  3. FastPitch
  4. FastSpeech 2 (TODO)

Through this API, any model can be trained in two ways. Either using pre-computed durations from a pre-trained Tacotron model or using an alignment network to learn durations from the dataset. The alignment network is only used at training and discarded at inference. You can set which mode you want to use by just setting the use_aligner field in the configuration.

This new API will help us to design more efficient inference run-time for all these models using ONNX like run-time optimizers.

Old FastPitch and SpeedySpeech implementations are deprecated for the sake of this new implementation.

Fine-Tuning Documentation

This version introduces documentation for model fine-tunning. You can see it under https://tts.readthedocs.io/ when this is merged.

New Model Releases
  • English Speedy Speech model on LJSpeech

Try out:

tts --test "This is a sample text for my model to speak." --model_name tts_models/en/ljspeech/speedy-speech
  • Fine-tuned UnivNet Vocoder

Try out:

tts --text "This is how it is." --model_name tts_models/en/ljspeech/tacotron2-DDC_ph

Files

coqui-ai/TTS-v0.3.0.zip

Files (15.0 MB)

Name Size Download all
md5:7377ee120bfeecc94dbdc7025ce39cd7
15.0 MB Preview Download

Additional details

Related works

Is supplement to
https://github.com/coqui-ai/TTS/tree/v0.3.0 (URL)