News on August 18,AlibabaRELEASE AI Music Model Happy Shrimp "Happy shrimp rice" in Chinese. Users can describe their music needs with emotion, story, memory or use of scenery, and the model completes the words, composes, composes and sings at the same time, producing a full song without having to break the hints into a tune, musical instrument or rhythm label。
HappyShrimp uses end-to-end wholesome generation to put language descriptions, lyrics, tunes, emotions, age, voice, tunes, BPM and mixers into the same planning process. It is officially stated that this method would synchronize the processing of linguistics, human sound and long-range structures, and reduce the linguistic mismatches and hearing loss caused by the hyphenation of segments。
HappyShrimp 1.0 is already on the PC page at the national and overseas levels and new users receive free credits. The official page also offers a view of the work and an entry for its creation。