media Hugging Face Forums · 2h ago · open_models

OpenGauntlet publishes catalog of 168 TTS and 106 STT systems

from English

A researcher has published the OpenGauntlet research catalog, a public resource containing information on 168 text-to-speech systems and 106 speech-to-text systems. The directories cover open and hosted models, licensing, hardware requirements, languages, capabilities, lifecycle status, source information, and published benchmark data where available.

168 text-to-speech systems listed in the Voices directory.
106 speech-to-text systems listed in the Listening directory.
Coverage includes open and hosted models with details on licensing and hardware requirements.
The catalog is a sourced research compilation, not a personal benchmark of all 274 systems.

The author seeks feedback from the community regarding missing models, stale entries, or incorrect license information to improve the resource.

Importance 1/3 Trust 1/3 Hugging Face Forums Training data Voice & audio

Read original

arxiv arXiv cs.CL · 27d ago

DuplexChat releases open-source corpus for full-dex dialogue speech modeling

Researchers introduce DuplexChat, an open-source corpus designed to address the lack of speaker-separated data needed for training full-duplex spoken dialogue language models. To create this resource, they developed DuplexChat-Pipe, a pipeline that processes public podcast feeds to extract and separate audio streams.

arxiv arXiv cs.CL · 29d ago

DuplexChat releases open-source corpus for full-dex dialogue speech modeling

LuxEmo: 21-hour expressive Luxembourgish TTS corpus

Audio-Based Understanding of Audiobook Narration Appeal

Monthly compliance matrix reveals 65% of 4,893 Indic datasets lack license tags

Calibra v0.7.1 adds dataset integrity checks for robot learning