Search Results for "corpora"

Style-Bert-VITS2 is a text-to-speech system based on Bert-VITS2 that focuses on highly controllable voice styles and emotional expression. It takes the original Bert-VITS2 v2.1 and its Japanese-Extra variant and extends them so you can control emotion and speaking style with fine-grained intensity, not just choose a generic tone. The project targets both power users and beginners: Windows users without Git or Python can install and run it using bundled .bat scripts, while advanced users can...

...The repository provides an end-to-end TTS pipeline: a PyTorch/Lightning training stack, configuration files, pre-trained checkpoints, a command-line interface, and a Gradio app for interactive testing. Users can train on standard datasets like LJSpeech or plug in their own corpora, with helper tools for computing dataset statistics, extracting phoneme durations, and running multi-GPU training.

WavTokenizer is a state-of-the-art discrete acoustic codec designed specifically for audio language modeling, capable of compressing 24 kHz audio into just 40 or 75 tokens per second while preserving high perceptual quality. It is built to represent speech, music, and general audio with extremely low bitrate, making it ideal as a front-end for large audio language models like GPT-4o and similar architectures. The model uses a single-quantizer design together with temporal compression to...

...The repository is designed to work hand-in-hand with ESPnet-TTS and NVIDIA Tacotron2-style front ends, so you can build complete TTS or singing voice synthesis pipelines. It includes a large collection of “Kaldi-style” recipes for many datasets such as LJSpeech, LibriTTS, VCTK, JSUT, CMU Arctic, and multiple singing voice corpora in Japanese, Mandarin, Korean, and more. The project provides pre-trained models, Colab demos, and example configurations, allowing researchers to quickly evaluate vocoder quality or adapt models to new datasets.

Open Speech Corpora is a curated catalog of speech datasets intended to support research and development in automatic speech recognition, text-to-speech, and other speech technologies. The repository is organized as a set of tables that list corpora along with their languages, total hours, number of speakers, download links, and licenses, giving practitioners a quick way to find data that matches their needs.

...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.