Back: Catalog

espnet

ESPnet is a PyTorch-based end-to-end speech processing toolkit. It supports many tasks such as speech recognition, text synthesis, speech translation, voice improvement, and speaker parsing. The Kaldi style includes repeatable recipes and hundreds of trained models.

ES

espnet

80

espnet · Voice & Text-to-Speech

STARS10.0K
FORKS2.4K
COMMITS0
CONTRIBUTORS0
VERSIONv.202610
UPDATEDyesterday
PythonPyTorchSpeech ProcessingASRApache-2.0

Common commercial products in this category: ElevenLabs, Amazon Polly, Google Cloud Text-to-Speech

What can it do?
  • You can extract from the command line via pre-trained models with a single-line command.
  • From data preparation to evaluation, you can run Kaldi style repeatable recipes.
  • With training components, you can train deep neural networks using the espnet upload.
Website GitHub

My note

Alternative pages

ElevenLabs alternativesAmazon Polly alternativesGoogle Cloud Text-to-Speech alternatives

More in: Voice & Text-to-Speech