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

Support multi-speaker preprocessing, training and inference #34

Merged
merged 24 commits into from
Jan 19, 2023
Merged
Changes from 1 commit
Commits
Show all changes
24 commits
Select commit Hold shift + click to select a range
77de178
Support multi-speaker preprocessing
yqzhishen Jan 13, 2023
025ccf8
Support multi-speaker preprocessing
yqzhishen Jan 13, 2023
bcd875c
Merge branch 'multi-spk' of https://github.com/openvpi/DiffSinger int…
yqzhishen Jan 14, 2023
45ffe4b
Save speaker id instead of speaker name
yqzhishen Jan 14, 2023
2f47002
Support speaker embedding
yxlllc Jan 14, 2023
6e46084
Fix yaml data type error
yqzhishen Jan 15, 2023
cdf9801
Fix item order
yqzhishen Jan 15, 2023
6a2716d
Copy spk map to work dir
yqzhishen Jan 15, 2023
1684028
Support multi-speaker preprocessing
yqzhishen Jan 13, 2023
0401704
Save speaker id instead of speaker name
yqzhishen Jan 14, 2023
b868e01
Support speaker embedding
yxlllc Jan 14, 2023
2fc5d15
Fix yaml data type error
yqzhishen Jan 15, 2023
20a6dd3
Fix item order
yqzhishen Jan 15, 2023
a6fecdb
Copy spk map to work dir
yqzhishen Jan 15, 2023
6430ab8
Merge branch 'multi-spk' of https://github.com/openvpi/DiffSinger int…
yqzhishen Jan 15, 2023
eded2bd
Support multi-speaker inference
yqzhishen Jan 16, 2023
9ee7405
Fix multi-speaker inference error
yqzhishen Jan 16, 2023
bbce763
Fix NoneType conversion to Tensor error caused by spk_id
yqzhishen Jan 16, 2023
20d152a
Support static speaker mix at inference time
yqzhishen Jan 18, 2023
7ecbb05
Support static speaker mix at inference time
yqzhishen Jan 18, 2023
0678e54
Check duplicate speaker id
yqzhishen Jan 18, 2023
d6924c4
Allow hyphen in speaker name
yqzhishen Jan 19, 2023
8929c27
Support configuring multiple datasets for combined models
yqzhishen Jan 19, 2023
fadac19
Support configuring multiple datasets for combined models
yqzhishen Jan 19, 2023
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
Prev Previous commit
Next Next commit
Check duplicate speaker id
  • Loading branch information
yqzhishen committed Jan 18, 2023
commit 0678e5451a35f91d7b6c0d0d6a3da9da18b0a846
1 change: 1 addition & 0 deletions basics/base_svs_infer.py
Original file line number Diff line number Diff line change
Expand Up @@ -49,6 +49,7 @@ def __init__(self, hparams, device=None, load_model=True, load_vocoder=True):
with open(os.path.join(hparams['work_dir'], 'spk_map.json'), 'r', encoding='utf8') as f:
self.spk_map = json.load(f)
assert isinstance(self.spk_map, dict) and len(self.spk_map) > 0, 'Invalid or empty speaker map!'
assert len(self.spk_map) == len(set(self.spk_map.values())), 'Duplicate speaker id in speaker map!'
self.model = self.build_model()
self.model.eval()
self.model.to(self.device)
Expand Down