Spoken Language Understanding: SPEECHMASSIVE Leaderboard

Models Average
intent_accuracy_standard_error slot_value_cer slot_type_f1 intent_accuracy_mean
SpeechLMM_v1.0_L base 0.006 1.000 0.000 0.857
SpeechLMM_v1.0_L_SLU 0.007 1.000 0.000 0.817
Models fr → fr
intent_accuracy_standard_error slot_value_cer slot_type_f1 intent_accuracy_mean
SpeechLMM_v1.0_L base 0.006 1.000 0.000 0.867
SpeechLMM_v1.0_L_SLU 0.007 1.000 0.000 0.821
Models de → de
intent_accuracy_standard_error slot_value_cer slot_type_f1 intent_accuracy_mean
SpeechLMM_v1.0_L base 0.007 1.000 0.000 0.847
SpeechLMM_v1.0_L_SLU 0.007 1.000 0.000 0.813