RuntimeError: The size of tensor a (225) must match the size of tensor b (96) at non-singleton dimension 2

[brianadit24]

This issue on WaveGrad trainer
I want to use hop_length=600 but its no working!

! CUDA_VISIBLE_DEVICES=0 python trisa_vocoder_trainer.py

Setting up Audio Processor...
| > sample_rate:48000
| > resample:False
| > num_mels:80
| > log_func:np.log10
| > min_level_db:-100
| > frame_shift_ms:None
| > frame_length_ms:None
| > ref_level_db:20
| > fft_size:4096
| > power:1.5
| > preemphasis:0.0
| > griffin_lim_iters:60
| > signal_norm:True
| > symmetric_norm:True
| > mel_fmin:0
| > mel_fmax:None
| > spec_gain:20.0
| > stft_pad_mode:reflect
| > max_norm:4.0
| > clip_norm:True
| > do_trim_silence:True
| > trim_db:45
| > do_sound_norm:False
| > do_amp_to_db_linear:True
| > do_amp_to_db_mel:True
| > do_rms_norm:False
| > db_level:None
| > stats_path:None
| > base:10
| > hop_length:600
| > win_length:2400
Using CUDA: True
Number of GPUs: 1

Traceback of TorchScript (most recent call last):
File "/home/brian.hermansyah/TTS/tts_env/lib/python3.8/site-packages/TTS/vocoder/layers/wavegrad.py", line 69, in shif_and_scale
@torch.jit.script
def shif_and_scale(x, scale, shift):
o = shift + scale * x
~~~~~~~~~ <--- HERE
return o
RuntimeError: The size of tensor a (225) must match the size of tensor b (96) at non-singleton dimension 2

i try to change seq_len=14400 but its still not working

How to handle this issue?