WaveGlow Speech Synthesis model with 88M Parameters
Model Overview
For model details, please refer to the main WaveGlow model page. This version contains a model that has 88 million parameters.
Trained or fine-tuned NeMo models (with the file extenstion .nemo) can be converted to Riva models (with the file extension .riva) and then deployed. Here is a pre-trained WaveGlow Speech Synthesis Riva model, again containing 88 million 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 WaveGlow
from nemo.collections.tts.models import WaveGlowModel
vocoder = WaveGlowModel.from_pretrained(model_name="tts_waveglow_88m")
# 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): An updated version of melgan that standardizes mel spectrogram generation across NeMo models.
1.0.0rc1: The original version that was released with NeMo 1.0.0.rc1
References
WaveGlow paper: https://arxiv.org/abs/1811.00002
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.