NGC | Catalog
CatalogModelsTTS Vocoder Uniglow

TTS Vocoder Uniglow

Logo for TTS Vocoder Uniglow
Description
UniGlow Speech Synthesis model
Publisher
NVIDIA
Latest Version
1.0.0rc1
Modified
April 4, 2023
Size
20.32 MB

Model Overview

UniGlow is a Glow-based (alternatively flow-based) model that generates audio from mel spectrograms.

Model Architecture

UniGlow improves upon WaveGlow by reducing the amount of parameters by 12x. WaveGlow has 12 glow layers, whereas UniGlow has 12 glow layers but each layer shares the same parameters.

Training

This model is trained on LJSpeech sampled at 22050Hz, and has been tested on generating female English voices with an American accent.

Performance

No performance information available at this time.

How to Use this Model

This model can be automatically loaded from NGC.

NOTE: In order to generate audio, you also need a spectrogram generator from NeMo. This example uses the FastPitch model.

# Load spectrogram generator
from nemo.collections.tts.models import FastPitchModel
spec_generator = FastPitchModel.from_pretrained("tts_en_fastpitch")

# Load uniglow
from nemo.collections.tts.models import UniGlowModel
vocoder = UniGlowModel.from_pretrained(model_name="tts_uniglow")

# 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 = vocoder.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)

Input

This model accepts batches of mel spectrograms.

Output

This model outputs audio at 22050Hz.

Limitations

There are no known limitations at this time.

Versions

1.0.0 (current): The original version that was released with NeMo 1.0.0

Licence

License to use this model is covered by the NGC TERMS OF USE unless another License/Terms Of Use/EULA is clearly specified. By downloading the public and release version of the model, you accept the terms and conditions of the NGC TERMS OF USE.