Adam

In the before test function mock the Disposable constructor. This should get rid of the error. @Before fun setUp() { mockkConstructor(Disposable::class) }

In the before test func mock the LocalDateTime constructor. This should get rid of the error. @Before fun setUp() { mockkConstructor(LocalDateTime::class) }

@sanchit-gandhi It would also be nice to use seeds to get consistent voices.

@Saltb0xApps I was thinking the same thing and also adding another input conditioning, like background music for the generated audio to follow. I am not exactly an ML engineer but...

@Saltb0xApps awesome please share some of your audio outputs when you can as the training proceeds.

My training code `from audiolm_pytorch import SoundStream, SoundStreamTrainer soundstream = SoundStream( codebook_size=1024, rq_num_quantizers=8, rq_groups=2, # 2 groups of quantizers attn_window_size=128, # local attention receptive field at bottleneck attn_depth=2 # 2...

Thanks. Also what is the difference between sample_31500.flac and sample_31500.ema.flac (EMA and non EMA Audio Samples). Which should I use to measure the performance of the soundstream model? @lucidrains

Okay. because the ema samples sound bad while the non Ema audio samples sound great. 😬 I'm at 38,000 steps and have been training for about 6 days now. What...