Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix the bug in the inference #127

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 22 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -129,6 +129,28 @@ Terminal Technology Department, Alipay, Ant Group.

</table>

### Audio Driven after fix the bug in schedule of inference

Left: After fixing the bug; Right: Before fixing the bug;
Fix the bug will remove the noise of background.

<table class="center">

<tr>
<td width=50% style="border: none">
<video controls loop src="https://github.com/user-attachments/assets/66b40f9a-69d9-4dba-853a-cbb7796ee9e2" muted="false"></video>
</td>
<td width=50% style="border: none">
<video controls loop src="https://github.com/user-attachments/assets/49a8c966-1ba9-4178-8650-b7919e266767" muted="false"></video>
</td>
</tr>

</table>





**(Some demo images above are sourced from image websites. If there is any infringement, we will immediately remove them and apologize.)**

## Installation
Expand Down
4 changes: 2 additions & 2 deletions configs/inference/inference_v2.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -25,12 +25,12 @@ unet_additional_kwargs:
noise_scheduler_kwargs:
beta_start: 0.00085
beta_end: 0.012
beta_schedule: "linear"
beta_schedule: "scaled_linear"
clip_sample: false
steps_offset: 1
### Zero-SNR params
prediction_type: "v_prediction"
rescale_betas_zero_snr: True
timestep_spacing: "trailing"

sampler: DDIM
sampler: DDIM