kaituoxu / 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
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Tacotron2
Wavernn
WaveRNN Vocoder + TTS
Stars: ✭ 1,636 (+3704.65%)
Mutual labels: speech-synthesis, tacotron, text-to-speech
Tacotron Pytorch
A Pytorch Implementation of Tacotron: End-to-end Text-to-speech Deep-Learning Model
Stars: ✭ 104 (+141.86%)
Mutual labels: speech-synthesis, tacotron, text-to-speech
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 (-48.84%)
Mutual labels: text-to-speech, speech-synthesis, tacotron
Tacotron 2
DeepMind's Tacotron-2 Tensorflow implementation
Stars: ✭ 1,968 (+4476.74%)
Mutual labels: speech-synthesis, tacotron, text-to-speech
Nnmnkwii
Library to build speech synthesis systems designed for easy and fast prototyping.
Stars: ✭ 308 (+616.28%)
Mutual labels: speech-synthesis, text-to-speech
Glow Tts
A Generative Flow for Text-to-Speech via Monotonic Alignment Search
Stars: ✭ 284 (+560.47%)
Mutual labels: speech-synthesis, text-to-speech
Tts
🤖 💬 Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)
Stars: ✭ 5,427 (+12520.93%)
Mutual labels: tacotron, text-to-speech
Tacotron pytorch
Tacotron implementation of pytorch
Stars: ✭ 12 (-72.09%)
Mutual labels: speech-synthesis, tacotron
Hifi Gan
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
Stars: ✭ 325 (+655.81%)
Mutual labels: speech-synthesis, text-to-speech
Espeak Ng
eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.
Stars: ✭ 799 (+1758.14%)
Mutual labels: speech-synthesis, text-to-speech
Parakeet
PAddle PARAllel text-to-speech toolKIT (supporting WaveFlow, WaveNet, Transformer TTS and Tacotron2)
Stars: ✭ 279 (+548.84%)
Mutual labels: speech-synthesis, text-to-speech
Tts
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
Stars: ✭ 305 (+609.3%)
Mutual labels: tacotron, text-to-speech
Cognitive Speech Tts
Microsoft Text-to-Speech API sample code in several languages, part of Cognitive Services.
Stars: ✭ 312 (+625.58%)
Mutual labels: speech-synthesis, text-to-speech
esp32-flite
Speech synthesis running on ESP32 based on Flite engine.
Stars: ✭ 28 (-34.88%)
Mutual labels: text-to-speech, speech-synthesis
Multilingual text to speech
An implementation of Tacotron 2 that supports multilingual experiments with parameter-sharing, code-switching, and voice cloning.
Stars: ✭ 324 (+653.49%)
Mutual labels: speech-synthesis, text-to-speech
Voice Builder
An opensource text-to-speech (TTS) voice building tool
Stars: ✭ 362 (+741.86%)
Mutual labels: speech-synthesis, text-to-speech
Lightspeech
LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Search
Stars: ✭ 31 (-27.91%)
Mutual labels: speech-synthesis, text-to-speech
Rhvoice
a free and open source speech synthesizer for Russian and other languages
Stars: ✭ 750 (+1644.19%)
Mutual labels: speech-synthesis, text-to-speech
leon
🧠 Leon is your open-source personal assistant.
Stars: ✭ 8,560 (+19806.98%)
Mutual labels: text-to-speech, speech-synthesis
Tacotron 2
A PyTorch implementation of Tacotron2, described in Natural TTS Synthesis By Conditioning Wavenet On Mel Spectrogram Predictions, an end-to-end text-to-speech(TTS) neural network architecture, which directly converts character text sequence to speech.
Install
- Python3.6+ (Recommend Anaconda)
- PyTorch 0.4.1+
pip install -r requirements.txt- If you want to run
egs/ljspeech/run.sh, download LJ Speech Dataset for free.
Usage
Quick start
$ cd egs/ljspeech
# Modify wav_dir to your LJ Speech dir
$ bash run.sh
That's all.
You can change parameter by $ bash run.sh --parameter_name parameter_value, egs, $ bash run.sh --stage 2. See parameter name in egs/ljspeech/run.sh before . utils/parse_options.sh.
Workflow
Workflow of egs/ljspeech/run.sh:
- Stage 1: Training
- Stage 2: Synthesising
More detail
egs/ljspeech/run.sh provide example usage.
# Set PATH and PYTHONPATH
$ cd egs/ljspeech/; . ./path.sh
# Train:
$ train.py -h
# Synthesis audio:
$ synthesis.py -h
How to visualize loss?
If you want to visualize your loss, you can use visdom to do that:
- Open a new terminal in your remote server (recommend tmux) and run
$ visdom - Open a new terminal and run
$ bash run.sh --visdom 1 --visdom_id "<any-string>"or$ train.py ... --visdom 1 --vidsdom_id "<any-string>" - Open your browser and type
<your-remote-server-ip>:8097, egs,127.0.0.1:8097 - In visdom website, chose
<any-string>inEnvironmentto see your loss
How to resume training?
$ bash run.sh --continue_from <model-path>
How to use multi-GPU?
Use comma separated gpu-id sequence, such as:
$ bash run.sh --id "0,1"
How to solve out of memory?
- When happened in training, try to reduce
batch_sizeor use more GPU.$ bash run.sh --batch_size <lower-value>or$ bash run.sh --id "0,1".
Reference and Resource
- https://github.com/NVIDIA/tacotron2
- https://github.com/A-Jacobson/tacotron2
- https://github.com/Rayhane-mamah/Tacotron-2
NOTE
This is a work in progress and any contribution is welcome (dev branch is main development branch).
I implement feature prediction network + Griffin-Lim to synthesis speech now.
Attention and synthesised audio on 37k iterations:
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].