Search Results for "community"

...This combination allows researchers to leverage modern neural architectures while still benefiting from the robust data preparation practices developed in the speech community. ESPnet provides many ready-to-run recipes for popular academic benchmarks, making it straightforward to reproduce published results or serve as baselines for new research. The toolkit also hosts numerous pretrained models and example configs, ranging from Transformer and Conformer architectures to various attention-based encoder-decoder models.

...It offers both a Gradio backend and an optional React frontend, which can be accessed on separate ports and even run inside Docker for more reproducible deployments. An extension system lets you enable extra models and tools, install community extensions from a catalog, and manage them via a dedicated GUI or CLI extension manager.

WhisperSpeech is an open-source text-to-speech system created by “inverting” OpenAI’s Whisper, reusing its strengths as a semantic audio model to generate speech instead of only transcribing it. The project aims to be for speech what Stable Diffusion is for images: powerful, hackable, and safe for commercial use, with code under Apache-2.0/MIT and models trained only on properly licensed data. Its architecture follows a token-based, multi-stage pipeline inspired by AudioLM and SPEAR-TTS:...

Audio Webui is a Gradio-based web user interface that unifies a wide range of audio-related neural networks under a single, accessible front end. It is designed as an “all-in-one” environment where users can experiment with text-to-speech, voice cloning, generative music, and other neural audio models without writing boilerplate code. The project supports multiple back-end models and toolchains (such as Bark, RVC, AudioLDM, Audiocraft, and other text-to-audio or voice-cloning tools),...

...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. It emphasizes free and truly “open” datasets, favoring those released under Creative Commons or community-friendly data licenses, though it also lists corpora that are accessible for research and many commercial uses. The catalog covers well-known resources such as Mozilla Common Voice, Yesno, LJ Speech and numerous Nordic and parliamentary speech corpora, along with their license variants like CC-0 and CC-BY. It is actively maintained as a community resource: users are encouraged to propose new corpora via issues, and there is a backlog of datasets waiting to be integrated.

MockingBird is an open-source voice cloning and real-time speech generation toolkit that lets you clone a speaker’s voice from a short audio sample (reportedly as little as 5 seconds) and then synthesize arbitrary speech in that voice. It builds on deep-learning based TTS / voice-cloning technology (in the lineage of projects such as Real-Time-Voice-Cloning), but extends it with support for Mandarin Chinese and multiple Chinese speech datasets — broadening its applicability beyond English....