This paper focuses on rolling elements bearing faults detection in induction machine based on stator currents monitoring. Specifically, it proposes to process the stator currents using Hilbert-Huang transform. This approach is composed of two steps. First, the empirical mode decomposition is used in order to estimate the intrinsic mode functions (IMFs), then the Hilbert transform is employed to compute the instantaneous amplitude (IA) and instantaneous frequency (IF). The energy of the instantaneous amplitude of the IMFs is used as fault indicator. The proposed approach is used for bearing fault detection in induction machine at several fault degrees. The effectiveness of the proposed Hilbert-Huang Transform technique is verified by a series of experimental tests corresponding to different bearing fault conditions.