hifigan-tr_tr-common

A vocoder by Coqui, from github.com/coqui-ai/TTS/releases/download/v0.6.1_models/vocoder_models--tr--common-voice--hifigan.zip, packaged for phoonnx, our ONNX text-to-speech library.

Model details

Architecture Vocoders
Upstream github.com/coqui-ai/TTS/releases/download/v0.6.1_models/vocoder_models--tr--common-voice--hifigan.zip
Author Coqui
Languages of the voices that use it tr-TR

How to use

This vocoder turns the spectrograms of the models below into audio. phoonnx downloads it with each of their voices, so it needs no step of its own.

Models that use it

The phoonnx voice index pairs these models and voices with this vocoder:

Licence

The upstream declares the licence MIT in the Coqui TTS model list.

Related projects

  • phoonnx: runs this model, in Python and in OVOS.
  • scriptconv: text normalisation, script conversion and phonemizers for phoonnx.
  • The Vocoders collection: every Vocoders model packaged for phoonnx.
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Collection including Phoonnx/hifigan-tr_tr-common