This is a large wav2vec 2.0 Conformer model with rotary position embeddings (RoPE), fine-tuned on 960 hours of English speech data. Developed by Facebook AI, it achieves strong performance on automatic speech recognition tasks. The model is hosted on Hugging Face and integrates with the Transformers library for easy inference.
Wav2vec2 Conformer Rope Large 960h Ft sits in PulseGate's Speech to text category. High-accuracy English speech-to-text transcription using a state-of-the-art self-supervised speech model. Wav2vec2 Conformer Rope Large 960h Ft is an open-source project aimed at developers. The project is open source (MIT). It ships for the web and API.
Behind Wav2vec2 Conformer Rope Large 960h Ft is Meta, based in the United States, and it first shipped in 2017. The GitHub repository has been archived. Among its 3 catalogued features are speech recognition, conformer architecture, and fine-tuned.
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