The FastPitch model generates mel-spectrograms from raw input text and allows to exert additional control over the synthesized utterances.
FastPitch is a fully feedforward Transformer model that predicts mel-spectrograms from raw text (Figure 1). The entire process is parallel, which means that all input letters are processed simultaneously to produce a full mel-spectrogram in a single forward pass.
Figure 1. Architecture of FastPitch (source). The model is composed of a bidirectional Transformer backbone (also known as a Transformer encoder), a pitch predictor, and a duration predictor. After passing through the first *N* Transformer blocks, encoding, the signal is augmented with pitch information and discretely upsampled. Then it goes through another set of *N* Transformer blocks, with the goal of smoothing out the upsampled signal, and constructing a mel-spectrogram.
This model was trained using script available in GitHub repo.
The following datasets were used to train this model:
- LJSpeech-1.1 - Dataset consisting of 13,100 short audio clips of a single speaker reading passages from 7 non-fiction books. A transcription is provided for each clip. Clips vary in length from 1 to 10 seconds and have a total length of approximately 24 hours.
Performance numbers for this model are available in GitHub readme performance section.