Moore Threads has announced the open-source release of its audio understanding model, MooER, making it the first large-scale open-source speech model based on domestically produced full-feature GPUs. MooER supports Chinese and English speech recognition and translation, utilizing a three-part model structure that demonstrates robust multilingual processing capabilities. The inference code and a model trained on 5000 hours of data have been released as open source, with plans to further open-source training code and an enhanced version trained on 80,000 hours of data. In comparative testing, MooER-5K has shown outstanding performance, achieving a Chinese CER of 4.21% and an English WER of 17.98%, particularly.

MoE Technology has announced the open-source release of its independently developed audio understanding large model, MooER, which is the first large-scale open-source speech model trained and inferred on domestically produced full-featured GPUs. MooER was trained on a large-scale audio dataset in just 38 hours on the MoE KuaE Intelligence Computing Platform, demonstrating excellent performance in Chinese and English speech recognition, as well as Chinese-to-English speech translation, achieving an impressive BLEU score of 25.2 in the Covost2 Chinese-to-English test set, nearing industrial-grade effectiveness. MoE Technology plans to further open-source the training code.

GPT-4o, OpenAI's flagship model released in May, stands out for its audio comprehension, achieving an average response time of 320 milliseconds, close to human conversation speed. It integrates text, visual, and audio modalities through end-to-end training, showcasing its potential across various inputs and outputs. OpenAI plans to launch advanced speech mode features via ChatGPT Plus in June, delayed by a month for improvements in model detectio....