The invention discloses a language recognition method. The method comprises the following steps: acquiring to-be-recognized audio data; extracting audio frequency domain features from the to-be-recognized audio data; based on the audio frequency domain features, carrying out sound accompanying data separation on the to-be-recognized audio data, thus obtaining to-be-recognized voice data, wherein the sound accompanying data separation is to separate the voice data and accompanying data from the audio data; and carrying out language recognition on the to-be-recognized voice data, thus obtaininga language recognition result of the to-be-recognized audio data. The invention further discloses a model training method, devices and a facility. According to the technical scheme, only the to-be-recognized voice data is input into a language recognition model, the part of the accompanying music is removed, so that the interference of the accompanying music on language recognition is reduced, andthe accuracy of song language recognition is improved.