FastPitch is a fully-parallel transformer architecture with prosody control over pitch and individual phoneme duration.
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.
For more details, please see Model Architecture or refer to the paper.
This model is trained on LJSpeech sampled at 22050Hz, and has been tested on generating female English voices with an American accent.
No performance information available at this time.
This model can be automatically loaded from NGC. NOTE: In order to generate audio, you also need a 22050Hz vocoder from NeMo. This example uses the HiFi-GAN model.
# Load Tacotron2 from nemo.collections.tts.models import FastPitchModel spec_generator = FastPitchModel.from_pretrained("tts_en_fastpitch") # Load vocoder from nemo.collections.tts.models import Vocoder model = Vocoder.from_pretrained(model_name="tts_hifigan") # Generate audio import soundfile as sf parsed = spec_generator.parse("You can type your sentence here to get nemo to produce speech.") spectrogram = spec_generator.generate_spectrogram(tokens=parsed) audio = model.convert_spectrogram_to_audio(spec=spectrogram) # Save the audio to disk in a file called speech.wav sf.write("speech.wav", audio.to('cpu').numpy(), 22050)
This model accepts batches of text.
This model generates mel spectrograms.
This checkpoint only works well with vocoders that were trained on 22050Hz data. Otherwise, the generated audio may be scratchy or choppy-sounding.
1.4.0 (current): An updated version trained using the new fastpitch_align.yaml file.
1.0.0: The original version released with NeMo 1.0.0.
Fastpitch paper: https://arxiv.org/abs/2006.06873