Open guofengjpggwk opened 1 year ago
test_result.zip "audio = net_g.infer(x_tst, x_tst_lengths, noise_scale=.667, noise_scale_w=0.8, length_scale=1.1)[0][0,0].data.cpu().float().numpy()"
I increased the value of length_scale, then the speed of synthesized speech slowed. But the last word of the audio doesn't sound clear.
test_result.zip "audio = net_g.infer(x_tst, x_tst_lengths, noise_scale=.667, noise_scale_w=0.8, length_scale=1.1)[0][0,0].data.cpu().float().numpy()"
I increased the value of length_scale, then the speed of synthesized speech slowed. But the last word of the audio doesn't sound clear.