Cannot run GMMHMM (Hidden Markov Model with Gaussain Mixture emissions in hmmlearn) with high number of mixtures

Question

I'm trying to use Gaussian Mixture Model within the hmmlearn package using the following configuration for a time series with 49792 samples:

model = GMMHMM(n_components=40, n_mix = 5, tol = 1e-6, covariance_type = "full", n_iter=100, verbose=True)

I get the following error:

ValueError: n_samples=3 should be >= n_clusters=5

I cannot comprehend why n_samples = 3 because of which the error is being thrown (It seems during the initial random clustering, the number of samples in some clusters become very less). Is there any way to get around this problem?