Model Overview

This collection contains two models:

1. FastPitch (around 50M parameters) trained on OpenSLR neutral German dataset with over 23 hours of German speech and 1 speaker.

2. HiFi-GAN trained on mel spectrograms produced by the FastPitch model in (1).

Model Architecture

FastPitch

FastPitch is non-autoregressive model for mel-spectrogram generation based on FastSpeech, conditioned on fundamental frequency contours. For more details about model, please refer to the original paper. Original FastPitch model uses an external Tacotron 2 model trained on LJSpeech-1.1 to extract training alignments and estimate durations of input symbols. This implementation of FastPitch is based on Deep Learning Examples, which uses an alignment mechanism proposed in RAD-TTS and extended in TTS Aligner.

For more information on training a basic FastPitch model, please refer to FastPitch_MixerTTS_Training.ipynb tutorial.

HiFi-GAN

HiFi-GAN is a generative adversarial network (GAN) model that generates audio from mel spectrograms. The generator uses transposed convolutions to upsample mel spectrograms to audio. For more details about the model, please refer to the original paper. NeMo re-implementation of HiFi-GAN can be found here.

Training

Datasets

FastPitch: This model is trained from scratch on one male speaker named Thorsten Müller from OpenSLR - German Neutral-TTS dataset sampled at 22050Hz. Link here.

HiFi-GAN: This model is derived after finetuning TTS Vocoder Hifigan v1.0.0rc1 (pretrained on English dataset) on predicted mel spectrograms from FastPitch above.

Performance

No performance information available at this time.

How to Use this Model

The model is available for use in the NeMo toolkit [4], and can be used as a pre-trained checkpoint for inference or for fine-tuning on another dataset.

NOTE: For best results you should use the vocoder (HiFiGAN) checkpoint in this model card along with the mel spectrogram generator (FastPitch) checkpoint.

Automatically load the model from NGC

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

# Load Vocoder
from nemo.collections.tts.models import HifiGanModel
model = HifiGanModel.from_pretrained(model_name="tts_de_openslr_hifigan_ft_fastpitch")

# Generate audio
import soundfile as sf
parsed = spec_generator.parse("Sie können Ihren Satz hier eingeben, um Nemo dazu zu bringen, Sprache zu produzieren.")
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)

Input

This model accepts batches of text.

Output

This model generates mel spectrograms.

Limitations

Since this model was trained on publically available speech datasets, the performance of this model might degrade for speech which includes technical terms, or vernacular that the model has not been trained on. The model might also perform worse for accented speech. This checkpoint only works well with vocoders that were trained on 22050Hz data. Otherwise, the generated audio may be scratchy or choppy-sounding.

Versions

• 1.15.0 (latest): This version applies grapheme-based tokenizer with grapheme-only symbol set, where the capitalization of each word is preserved. It includes FastPitch and HifiGan models trained on Thorsten's Neutral Datasets 21.02 and 22.10, respectively. There are four model checkpoints available.
• 1.10.0: This version applies phoneme-based tokenizer with the symbol set mixed with both phonemes and graphemes on Thorsten's Neural 21.02 dataset, where sentenc-level grapheme sequence and phoneme sequence for each transcript are considered as valid inputs. The version of FastPitch 1.1 without energy conditioning, see details here.

References

[1] FastPitch: https://arxiv.org/abs/2006.06873

[2] One TTS Alignment To Rule Them All: https://arxiv.org/abs/2108.10447

[3] HiFi-GAN paper: https://arxiv.org/abs/2010.05646

[4] NVIDIA NeMo Toolkit

NVIDIA License

1. Definitions

"Licensor" means any person or entity that distributes its Work.

"Work" means (a) the original work of authorship made available under this license, which may include software, documentation, or other files, and (b) any additions to or derivative works thereof that are made available under this license.

The terms "reproduce," "reproduction," "derivative works," and "distribution" have the meaning as provided under U.S. copyright law; provided, however, that for the purposes of this license, derivative works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work.

Works are "made available" under this license by including in or with the Work either (a) a copyright notice referencing the applicability of this license to the Work, or (b) a copy of this license.

2. License Grant

2.1 Copyright Grant. Subject to the terms and conditions of this license, each Licensor grants to you a perpetual, worldwide, non-exclusive, royalty-free, copyright license to use, reproduce, prepare derivative works of, publicly display, publicly perform, sublicense and distribute its Work and any resulting derivative works in any form.

3. Limitations

3.1 Redistribution. You may reproduce or distribute the Work only if (a) you do so under this license, (b) you include a complete copy of this license with your distribution, and (c) you retain without modification any copyright, patent, trademark, or attribution notices that are present in the Work.

3.2 Derivative Works. You may specify that additional or different terms apply to the use, reproduction, and distribution of your derivative works of the Work ("Your Terms") only if (a) Your Terms provide that the use limitation in Section 3.3 applies to your derivative works, and (b) you identify the specific derivative works that are subject to Your Terms. Notwithstanding Your Terms, this license (including the redistribution requirements in Section 3.1) will continue to apply to the Work itself.

3.3 Use Limitation. The Work and any derivative works thereof only may be used or intended for use non-commercially. Notwithstanding the foregoing, NVIDIA Corporation and its affiliates may use the Work and any derivative works commercially. As used herein, "non-commercially" means for research or evaluation purposes only.

3.4 Patent Claims. If you bring or threaten to bring a patent claim against any Licensor (including any claim, cross-claim or counterclaim in a lawsuit) to enforce any patents that you allege are infringed by any Work, then your rights under this license from such Licensor (including the grant in Section 2.1) will terminate immediately.

3.5 Trademarks. This license does not grant any rights to use any Licensor's or its affiliates' names, logos, or trademarks, except as necessary to reproduce the notices described in this license.

3.6 Termination. If you violate any term of this license, then your rights under this license (including the grant in Section 2.1) will terminate immediately.

4. Disclaimer of Warranty.

THE WORK IS PROVIDED "AS IS" WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, EITHER EXPRESS OR IMPLIED, INCLUDING WARRANTIES OR CONDITIONS OF

MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, TITLE OR NON-INFRINGEMENT. YOU BEAR THE RISK OF UNDERTAKING ANY ACTIVITIES UNDER THIS LICENSE.

5. Limitation of Liability.

EXCEPT AS PROHIBITED BY APPLICABLE LAW, IN NO EVENT AND UNDER NO LEGAL THEORY, WHETHER IN TORT (INCLUDING NEGLIGENCE), CONTRACT, OR OTHERWISE SHALL ANY LICENSOR BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY DIRECT, INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES ARISING OUT OF OR RELATED TO THIS LICENSE, THE USE OR INABILITY TO USE THE WORK (INCLUDING BUT NOT LIMITED TO LOSS OF GOODWILL, BUSINESS INTERRUPTION, LOST PROFITS OR DATA, COMPUTER FAILURE OR MALFUNCTION, OR ANY OTHER DAMAGES OR LOSSES), EVEN IF THE LICENSOR HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.