Everything tagged speech-recognition.
IBM released a new Granite Speech 5.0 2B model and updated two existing checkpoints, expanding multilingual transcription and translation, edge…
MBZUAI’s Institute of Foundation Models and Inception42 launched six Jais 3 text models plus Jais-ASR for Arabic-language writing, speech and agent…
Technology Innovation Institute has introduced Falcon-ASR, a 1.6-billion-parameter speech-recognition model focused on Arabic and Emirati speech,…
Apple researchers report compressing streaming audio encoders by 2.8-fold or more while five of six tested students stayed within 1.9% relative word…
