[Model] Add Ming-omni-tts MoE 16.8B-A3B + CFM CUDAGraph (#4341)
Signed-off-by: LHXuuu <xulianhao.xlh@antgroup.com> Signed-off-by: Yuanheng Zhao <jonathan.zhaoyh@gmail.com> Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com> Co-authored-by: Yuanheng Zhao <jonathan.zhaoyh@gmail.com> Co-authored-by: Yuanheng Zhao <54058983+yuanheng-zhao@users.noreply.github.com> Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
17 files changed
+637
-57
No files matched your search
@@ -346,11 +346,8 @@ class AudioVAE(PreTrainedModel):
|
||||
h, _ = self.encoder(waveform)
|
||||
h = h.transpose(1, 2)
|
||||
|
||||
mean, logvar = torch.chunk(h, 2, dim=1)
|
||||
logvar = torch.clamp(logvar, -30.0, 20.0)
|
||||
std = torch.exp(0.5 * logvar)
|
||||
latent = mean + std * torch.randn_like(mean)
|
||||
latent = latent.transpose(1, 2)
|
||||
mean = torch.chunk(h, 2, dim=1)[0]
|
||||
latent = mean.transpose(1, 2)
|
||||
return latent, frame_num
|
||||
|
||||
@torch.inference_mode()
|
||||
|
||||
Reference in new issue
Block a user