wav2vec2-large-robust-ft-swbd-300h is an open-weight automatic speech recognition model fine-tuned on 300 hours of Switchboard data. Developers can run it locally with the Transformers library for speech-to-text applications.
In the Speech to text space, Wav2vec2 Large Robust Ft Swbd 300h takes a focused approach. It focuses on converting spoken audio into text for speech recognition applications. It is built as an open-source project for machine learning developers. The project is open source (MIT). It ships for the web and the command line, and it can be self-hosted.
Behind Wav2vec2 Large Robust Ft Swbd 300h is Meta AI, and it first shipped in 2019. The GitHub repository has been archived. Among its 5 catalogued features are speech recognition, wav2Vec2 architecture, and pyTorch support.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do