PaddlePaddle / Parakeet
Licence: other
PAddle PARAllel text-to-speech toolKIT (supporting WaveFlow, WaveNet, Transformer TTS and Tacotron2)
Stars: ✭ 279
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Parakeet
Comprehensive-Tacotron2
PyTorch Implementation of Google's Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions. This implementation supports both single-, multi-speaker TTS and several techniques to enforce the robustness and efficiency of the model.
Stars: ✭ 22 (-92.11%)
Mutual labels: text-to-speech, tts, speech-synthesis
Parallel-Tacotron2
PyTorch Implementation of Google's Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling
Stars: ✭ 149 (-46.59%)
Mutual labels: text-to-speech, tts, speech-synthesis
Cross-Speaker-Emotion-Transfer
PyTorch Implementation of ByteDance's Cross-speaker Emotion Transfer Based on Speaker Condition Layer Normalization and Semi-Supervised Training in Text-To-Speech
Stars: ✭ 107 (-61.65%)
Mutual labels: text-to-speech, tts, speech-synthesis
ttslearn
ttslearn: Library for Pythonで学ぶ音声合成 (Text-to-speech with Python)
Stars: ✭ 158 (-43.37%)
Mutual labels: text-to-speech, tts, speech-synthesis
editts
Official implementation of EdiTTS: Score-based Editing for Controllable Text-to-Speech
Stars: ✭ 74 (-73.48%)
Mutual labels: text-to-speech, tts, speech-synthesis
Zero-Shot-TTS
Unofficial Implementation of Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration
Stars: ✭ 33 (-88.17%)
Mutual labels: text-to-speech, tts, speech-synthesis
spokestack-android
Extensible Android mobile voice framework: wakeword, ASR, NLU, and TTS. Easily add voice to any Android app!
Stars: ✭ 52 (-81.36%)
Mutual labels: text-to-speech, tts, speech-synthesis
Expressive-FastSpeech2
PyTorch Implementation of Non-autoregressive Expressive (emotional, conversational) TTS based on FastSpeech2, supporting English, Korean, and your own languages.
Stars: ✭ 139 (-50.18%)
Mutual labels: text-to-speech, tts, speech-synthesis
Daft-Exprt
PyTorch Implementation of Daft-Exprt: Robust Prosody Transfer Across Speakers for Expressive Speech Synthesis
Stars: ✭ 41 (-85.3%)
Mutual labels: text-to-speech, tts, speech-synthesis
open-speech-corpora
💎 A list of accessible speech corpora for ASR, TTS, and other Speech Technologies
Stars: ✭ 841 (+201.43%)
Mutual labels: text-to-speech, tts, speech-synthesis
LVCNet
LVCNet: Efficient Condition-Dependent Modeling Network for Waveform Generation
Stars: ✭ 67 (-75.99%)
Mutual labels: text-to-speech, tts, speech-synthesis
Fre-GAN-pytorch
Fre-GAN: Adversarial Frequency-consistent Audio Synthesis
Stars: ✭ 73 (-73.84%)
Mutual labels: text-to-speech, tts, speech-synthesis
TensorVox
Desktop application for neural speech synthesis written in C++
Stars: ✭ 140 (-49.82%)
Mutual labels: text-to-speech, tts, speech-synthesis
talkie
Text-to-speech browser extension button. Select text on any web page, and have the computer read it out loud for you by simply clicking the Talkie button.
Stars: ✭ 43 (-84.59%)
Mutual labels: text-to-speech, tts, speech-synthesis
StyleSpeech
Official implementation of Meta-StyleSpeech and StyleSpeech
Stars: ✭ 161 (-42.29%)
Mutual labels: text-to-speech, tts, speech-synthesis
VAENAR-TTS
PyTorch Implementation of VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis.
Stars: ✭ 66 (-76.34%)
Mutual labels: text-to-speech, tts, speech-synthesis
react-native-spokestack
Spokestack: give your React Native app a voice interface!
Stars: ✭ 53 (-81%)
Mutual labels: text-to-speech, tts, speech-synthesis
vits
VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
Stars: ✭ 1,604 (+474.91%)
Mutual labels: text-to-speech, tts, speech-synthesis
AdaSpeech
AdaSpeech: Adaptive Text to Speech for Custom Voice
Stars: ✭ 108 (-61.29%)
Mutual labels: text-to-speech, tts, speech-synthesis
WaveGrad2
PyTorch Implementation of Google Brain's WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis
Stars: ✭ 55 (-80.29%)
Mutual labels: text-to-speech, tts, speech-synthesis
Parakeet
Parakeet aims to provide a flexible, efficient and state-of-the-art text-to-speech toolkit for the open-source community. It is built on PaddlePaddle Fluid dynamic graph and includes many influential TTS models proposed by Baidu Research and other research groups.
In particular, it features the latest WaveFlow model proposed by Baidu Research.
- WaveFlow can synthesize 22.05 kHz high-fidelity speech around 40x faster than real-time on a Nvidia V100 GPU without engineered inference kernels, which is faster than WaveGlow and serveral orders of magnitude faster than WaveNet.
- WaveFlow is a small-footprint flow-based model for raw audio. It has only 5.9M parameters, which is 15x smalller than WaveGlow (87.9M).
- WaveFlow is directly trained with maximum likelihood without probability density distillation and auxiliary losses as used in Parallel WaveNet and ClariNet, which simplifies the training pipeline and reduces the cost of development.
Overview
In order to facilitate exploiting the existing TTS models directly and developing the new ones, Parakeet selects typical models and provides their reference implementations in PaddlePaddle. Further more, Parakeet abstracts the TTS pipeline and standardizes the procedure of data preprocessing, common modules sharing, model configuration, and the process of training and synthesis. The models supported here include Vocoders and end-to-end TTS models:
-
Vocoders
-
TTS models
And more will be added in the future.
Setup
Make sure the library libsndfile1 is installed, e.g., on Ubuntu.
sudo apt-get install libsndfile1
Install PaddlePaddle
See install for more details. This repo requires PaddlePaddle 2.0.0rc1 or above.
Install Parakeet
pip install -U paddle-parakeet
or
git clone https://github.com/PaddlePaddle/Parakeet
cd Parakeet
pip install -e .
See install for more details.
Examples
Entries to the introduction, and the launch of training and synthsis for different example models:
Audio samples
TTS models (Acoustic Model + Neural Vocoder)
Check our website for audio sampels.
Pretrained models
Models pretrained on LJSpeech can be downloaded here.
tacotron2 transformert_tts waveflow_res_128
Copyright and License
Parakeet is provided under the Apache-2.0 license.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].