KinglittleQ / Gst Tacotron
Licence: mit
A PyTorch implementation of Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
Stars: ✭ 175
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Gst Tacotron
Tacotron
A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model (unofficial)
Stars: ✭ 2,581 (+1374.86%)
Mutual labels: tacotron, tts
Tacotron2-PyTorch
Yet another PyTorch implementation of Tacotron 2 with reduction factor and faster training speed.
Stars: ✭ 118 (-32.57%)
Mutual labels: tts, tacotron
FCH-TTS
A fast Text-to-Speech (TTS) model. Work well for English, Mandarin/Chinese, Japanese, Korean, Russian and Tibetan (so far). 快速语音合成模型,适用于英语、普通话/中文、日语、韩语、俄语和藏语(当前已测试)。
Stars: ✭ 154 (-12%)
Mutual labels: tts, tacotron
Tts
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
Stars: ✭ 305 (+74.29%)
Mutual labels: tacotron, tts
Mimic Recording Studio
Mimic Recording Studio is a Docker-based application you can install to record voice samples, which can then be trained into a TTS voice with Mimic2
Stars: ✭ 202 (+15.43%)
Mutual labels: tacotron, tts
TTS tf
WIP Tensorflow implementation of https://github.com/mozilla/TTS
Stars: ✭ 14 (-92%)
Mutual labels: tts, tacotron
Multi Tacotron Voice Cloning
Phoneme multilingual(Russian-English) voice cloning based on
Stars: ✭ 192 (+9.71%)
Mutual labels: tacotron, tts
Tts
🤖 💬 Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)
Stars: ✭ 5,427 (+3001.14%)
Mutual labels: tacotron, tts
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 (-87.43%)
Mutual labels: tts, tacotron
tacotron2
Multispeaker & Emotional TTS based on Tacotron 2 and Waveglow
Stars: ✭ 102 (-41.71%)
Mutual labels: tts, tacotron
Text-to-Speech-Landscape
No description or website provided.
Stars: ✭ 31 (-82.29%)
Mutual labels: tts, tacotron
Tacotron
Audio samples accompanying publications related to Tacotron, an end-to-end speech synthesis model.
Stars: ✭ 493 (+181.71%)
Mutual labels: tacotron, tts
Awesome Speech Recognition Speech Synthesis Papers
Automatic Speech Recognition (ASR), Speaker Verification, Speech Synthesis, Text-to-Speech (TTS), Language Modelling, Singing Voice Synthesis (SVS), Voice Conversion (VC)
Stars: ✭ 2,085 (+1091.43%)
Mutual labels: tts
Marytts
MARY TTS -- an open-source, multilingual text-to-speech synthesis system written in pure java
Stars: ✭ 1,699 (+870.86%)
Mutual labels: tts
Pytorch Dc Tts
Text to Speech with PyTorch (English and Mongolian)
Stars: ✭ 122 (-30.29%)
Mutual labels: tts
GST-Tacotron-Pytorch
A PyTorch implementation of Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
Update
Add support for blizzard dataset.
Requirements
pip3 install -r requirements.txt
File structure
-
Hyperparameters.py
--- hyperparameters -
Network.py
--- encoder and decoder -
Modules.py
--- some modules for tacotron -
Loss.py
--- loss function -
Data.py
--- dataset loader -
utils.py
--- some util functions for data I/O -
Synthesis.py
--- speech generation
How to train
- Download a multispeaker dataset
- Preprocess your data and implement your
get_XX_data
function inData.py
- Set hyperparameters in
Hyperparameters.py
- Make a directory named
log
as follow:
--- log
| |
| --- log[log_number]
|
--- code
|
--- Tacotron
|
--- train.py
|
--- Network.py
|
......
- Run train.py
python3 train.py [log_number] [dataset_size] [start_epoch]
[log_number]: the log directory number
[dataset_size]: int or all
[start_epoch]: which epoch start to train (0 if start from scratch )
for example:
python3 train.py 0 all 0
How to generate wav
Rungenerate.py
. Replace the text
in generate.py
with any chinese sentences as you like before running
The pretained model provided is trained on Chinese dataset, so it only supports chinese now.
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].