Fitting gaussianlike model to data does not work?

Question

I want to fit this data.

I have the following model function.

    def losvd_param(v, v_rot, v_disp, h3, h4):
    y = np.asarray((np.asarray(v)-v_rot)/(v_disp))        # define new variably y for compact notation
    return (np.exp(-0.5 * y**2) * (1 + h3*((2*np.sqrt(2)*y**3-3*np.sqrt(2)*y)/np.sqrt(6)) + h4*((4*y**4-12*y**2+3)/np.sqrt(24))))

The 4 parameters refer to: x-value of maximum, width of the distribution, skewness and kurtosis.

I use curve_fit() to fit my data:

    gh_moments = curve_fit(losvd_param, vel_corr_peak, broadening_func)[0]

and get the unexpected output [1. 1. 1. 1.] which is clearly not correct it should more be something like [1318, 300, 0, 0], putting these values in mannually into my model function I roughly get the right fit to my data. I also get the warning:

OptimizeWarning: Covariance of the parameters could not be estimated

Can anybody tell me why this could be the case ? Edit: I get the same results, when I use a different model function simple gaussian. Using a linear model I get the fit is "working", so it might be something connected to the gaussian function ? (Note that my x-array goes from values rougly 500-2250)