NGC | Catalog
CatalogModelsTTS FastPitch speaker adapter pretrain IPA

TTS FastPitch speaker adapter pretrain IPA

For downloads and more information, please view on a desktop device.
Logo for TTS FastPitch speaker adapter pretrain IPA


Pretrained FastPitch base checkpoint for speaker adapter with IPA



Latest Version



November 9, 2023


197.92 MB

Speech Synthesis: FastPitch_Speaker_Adapter 1.1 Model

Model overview

FastPitch is a mel-spectrogram generator, designed to be used as the first part of a neural text-to-speech system in conjunction with a neural vocoder. This model was trained with adapters and is good for finetuning a custom voice, it also uses the International Phonetic Alphabet (IPA) for inference and training instead of ARPABET.

Model architecture

FastPitch is a fully-parallel text-to-speech model based on FastSpeech, conditioned on fundamental frequency contours. The model predicts pitch contours during inference. By altering these predictions, the generated speech can be more expressive, better match the semantic of the utterance, and in the end more engaging to the listener. FastPitch is based on a fully-parallel Transformer architecture, with much higher real-time factor than Tacotron2 for mel-spectrogram synthesis of a typical utterance.



This model is trained on a proprietary dataset sampled at 44100Hz, and can be used to generate English voices with an American accent. This model supports 1 male voice and 1 female voice.

How to use this model

FastPitch is intended to be used as the first part of a two stage speech synthesis pipeline. FastPitch takes text and produces a mel spectrogram. The second stage takes the generated mel spectrogram and returns audio.


English text strings


Mel spectrogram of shape (batch x mel_channels x time)


FastPitch with adapters paper:


By downloading and using the models and resources packaged with Riva Conversational AI, you would be accepting the terms of the Riva license

Ethical AI

NVIDIA’s platforms and application frameworks enable developers to build a wide array of AI applications. Consider potential algorithmic bias when choosing or creating the models being deployed. Work with the model’s developer to ensure that it meets the requirements for the relevant industry and use case; that the necessary instruction and documentation are provided to understand error rates, confidence intervals, and results; and that the model is being used under the conditions and in the manner intended.