This is the Linux app named Tacotron-2 whose latest release can be downloaded as Tacotron-2sourcecode.tar.gz. It can be run online in the free hosting provider OnWorks for workstations.
Download and run online this app named Tacotron-2 with OnWorks for free.
Follow these instructions in order to run this app:
- 1. Downloaded this application in your PC.
- 2. Enter in our file manager https://www.onworks.net/myfiles.php?username=XXXXX with the username that you want.
- 3. Upload this application in such filemanager.
- 4. Start the OnWorks Linux online or Windows online emulator or MACOS online emulator from this website.
- 5. From the OnWorks Linux OS you have just started, goto our file manager https://www.onworks.net/myfiles.php?username=XXXXX with the username that you want.
- 6. Download the application, install it and run it.
SCREENSHOTS
Ad
Tacotron-2
DESCRIPTION
Tacotron-2 is a TensorFlow implementation of DeepMind’s Tacotron-2 end-to-end text-to-speech architecture, which predicts mel spectrograms from raw text and then feeds them to a neural vocoder such as WaveNet. It reproduces the original paper’s hyperparameters exactly via paper_hparams.py, while also offering a tuned hparams.py with extra improvements that often yield better audio quality in practice. The repository is structured as a full training pipeline: dataset preparation, preprocessing into spectrograms, Tacotron training, WaveNet (or Griffin-Lim) vocoder training, and final waveform synthesis. It includes directory layouts and logging directories for multiple datasets such as LJSpeech and M-AILABS en_US/en_UK, making it easier to adapt to new English corpora. Separate log trees track mel-spectrograms, attention plots, evaluation audio, and vocoder outputs, so you can inspect how alignment and audio quality evolve over time.
Features
- Full TensorFlow implementation of Tacotron-2 with paper-accurate and enhanced hyperparameter sets
- End-to-end pipeline from raw audio datasets (e.g., LJSpeech, M-AILABS) through preprocessing, Tacotron training, and vocoder training
- Support for both WaveNet vocoder and Griffin-Lim inversion for mel-to-waveform synthesis
- Detailed repository structure with logs for mel-spectrograms, attention plots, evaluation audio, and vocoder outputs
- Modular training scripts (preprocess.py, train.py, synthesize.py, wavenet_preprocess.py) for flexible experimentation
- Example configurations that replicate the original paper results and variants that push for improved stability and quality
Programming Language
Python
Categories
This is an application that can also be fetched from https://sourceforge.net/projects/tacotron-2.mirror/. It has been hosted in OnWorks in order to be run online in an easiest way from one of our free Operative Systems.
