GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → root20 → Tacotron_pytorch

root20 / Tacotron_pytorch

Licence: Apache-2.0 License
Tacotron implementation of pytorch

Programming Languages

python
139335 projects - #7 most used programming language

Labels

pytorchspeech-synthesistacotron

Projects that are alternatives of or similar to Tacotron pytorch

mimic2
Text to Speech engine based on the Tacotron architecture, initially implemented by Keith Ito.
Stars: ✭ 537 (+4375%)
Mutual labels:  speech-synthesis, tacotron
Tacotron Pytorch
A Pytorch Implementation of Tacotron: End-to-end Text-to-speech Deep-Learning Model
Stars: ✭ 104 (+766.67%)
Mutual labels:  speech-synthesis, tacotron
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 (+83.33%)
Mutual labels:  speech-synthesis, tacotron
Wavernn
WaveRNN Vocoder + TTS
Stars: ✭ 1,636 (+13533.33%)
Mutual labels:  speech-synthesis, tacotron
Expressive tacotron
Tensorflow Implementation of Expressive Tacotron
Stars: ✭ 192 (+1500%)
Mutual labels:  speech-synthesis, tacotron
Tacotron pytorch
PyTorch implementation of Tacotron speech synthesis model.
Stars: ✭ 242 (+1916.67%)
Mutual labels:  speech-synthesis, tacotron
Tacotron2
A PyTorch implementation of Tacotron2, an end-to-end text-to-speech(TTS) system described in "Natural TTS Synthesis By Conditioning Wavenet On Mel Spectrogram Predictions".
Stars: ✭ 43 (+258.33%)
Mutual labels:  speech-synthesis, tacotron
Xva Synth
Machine learning based speech synthesis Electron app, with voices from specific characters from video games
Stars: ✭ 136 (+1033.33%)
Mutual labels:  speech-synthesis, tacotron
Tacotron 2
DeepMind's Tacotron-2 Tensorflow implementation
Stars: ✭ 1,968 (+16300%)
Mutual labels:  speech-synthesis, tacotron
Tacotron
A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model (unofficial)
Stars: ✭ 2,581 (+21408.33%)
Mutual labels:  speech-synthesis, tacotron
tacotron2
Pytorch implementation of "Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions", ICASSP, 2018.
Stars: ✭ 17 (+41.67%)
Mutual labels:  speech-synthesis, tacotron
Neural-HMM
Neural HMMs are all you need (for high-quality attention-free TTS)
Stars: ✭ 69 (+475%)
Mutual labels:  speech-synthesis
YourTTS
YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone
Stars: ✭ 217 (+1708.33%)
Mutual labels:  speech-synthesis
Fre-GAN-pytorch
Fre-GAN: Adversarial Frequency-consistent Audio Synthesis
Stars: ✭ 73 (+508.33%)
Mutual labels:  speech-synthesis
spoken-word
Spoken Word
Stars: ✭ 46 (+283.33%)
Mutual labels:  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 (+258.33%)
Mutual labels:  speech-synthesis
Voice2Mesh
CVPR 2022: Cross-Modal Perceptionist: Can Face Geometry be Gleaned from Voices?
Stars: ✭ 67 (+458.33%)
Mutual labels:  speech-synthesis
ExtensibleTTS-PyTorch
An extensible speech synthesis system, build with PyTorch and the original code is from r9y9's https://github.com/r9y9/nnmnkwii_gallery
Stars: ✭ 25 (+108.33%)
Mutual labels:  speech-synthesis
klatt-syn
Klatt formant synthesizer
Stars: ✭ 18 (+50%)
Mutual labels:  speech-synthesis
editts
Official implementation of EdiTTS: Score-based Editing for Controllable Text-to-Speech
Stars: ✭ 74 (+516.67%)
Mutual labels:  speech-synthesis
View All Similar Projects ➔

Tacotron_pytorch

Pytorch implementation of Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model

https://arxiv.org/abs/1703.10135

Requirements

  • pytorch
  • librosa
  • py-webrtcvad

Data

Please register to use Blizzard Challenge data set. (http://www.cstr.ed.ac.uk/projects/blizzard/)

In the code, the option 'blizzard' is for the Blizzard Challenge data of 2013.

The option 'etri' is for Korean TTS dataset published by 'ETRI' and you need to buy license to use it.

You need to download and unzip the data from the website.

Then, set paths in the codes (train.py, preprocess.py, generate.py) accordingly. (find 'dir_' and change the following lines)

How to run

  • Please refer the code to see what options/hyperparameters are available
  1. Prepare data and preprocess the data (ex. blizzard) by running: preprocess.py --data 'blizzard' (You may want to trim silences in audio files before preprocessing. Please use trimmer.py)
  2. Run 'train.py' with arguments.
  3. After training, run 'generate.py' with arguments to get generated audio file.

Comment

Contributions and comments are always welcome.

I refered https://github.com/keithito/tacotron for the preprocessing code. Thank you.

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].