S2T Small Librispeech ASR is an open-source speech-to-text model published by Facebook (Meta) and trained on the LibriSpeech corpus. It uses a sequence-to-sequence transformer architecture to perform automatic speech recognition, primarily for English audio. The model is available on Hugging Face for developers to integrate into transcription pipelines, run locally, or fine-tune for domain-specific audio recognition tasks.
In the Speech to text space, S2t Small Librispeech Asr takes a focused approach. It focuses on converting English audio speech from books or readings into accurate text transcripts. It is built as an open-source project for developers. The project is open source (MIT). It ships for the web, the command line, and API, and it can be self-hosted.
It is developed by Facebook, and it first shipped in 2017. The GitHub repository has been archived. Key capabilities include automatic speech recognition, libriSpeech pretrained, and transformer-based. It exposes integrations via a public API.
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