Skip to content
This repository has been archived by the owner on Nov 11, 2023. It is now read-only.

Commit

Permalink
Merge pull request #373 from CNChTu/4.1-Fork
Browse files Browse the repository at this point in the history
Debug
  • Loading branch information
ylzz1997 committed Sep 17, 2023
2 parents fec31b3 + 4e402d8 commit 68802ec
Show file tree
Hide file tree
Showing 11 changed files with 718 additions and 122 deletions.
2 changes: 2 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -519,6 +519,8 @@ Note: For Hubert Onnx models, please use the models provided by MoeSS. Currently
|[2105.02446v3](https://arxiv.org/abs/2105.02446v3) | Shallow Diffusion (PostProcessing)| DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism | [CNChTu/Diffusion-SVC](https://github.com/CNChTu/Diffusion-SVC) |
|[K-means](https://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=01D65490BADCC216F350D06F84D721AD?doi=10.1.1.308.8619&rep=rep1&type=pdf) | Feature K-means Clustering (PreProcessing)| Some methods for classification and analysis of multivariate observations | This repo |
| | Feature TopK Retrieval (PreProcessing)| Retrieval based Voice Conversion | [RVC-Project/Retrieval-based-Voice-Conversion-WebUI](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI) |
| | whisper ppg| whisper ppg | [PlayVoice/whisper_ppg](https://github.com/PlayVoice/whisper_ppg) |
| | bigvgan| bigvgan | [PlayVoice/so-vits-svc-5.0](https://github.com/PlayVoice/so-vits-svc-5.0/tree/bigvgan-mix-v2/vits_decoder/alias) |


## ☀️ Previous contributors
Expand Down
74 changes: 0 additions & 74 deletions diffusion/infer_gt_mel.py

This file was deleted.

3 changes: 2 additions & 1 deletion diffusion/solver.py
Original file line number Diff line number Diff line change
Expand Up @@ -101,6 +101,7 @@ def train(args, initial_global_step, model, optimizer, scheduler, vocoder, loade

# run
num_batches = len(loader_train)
start_epoch = initial_global_step // num_batches
model.train()
saver.log_info('======= start training =======')
scaler = GradScaler()
Expand All @@ -113,7 +114,7 @@ def train(args, initial_global_step, model, optimizer, scheduler, vocoder, loade
else:
raise ValueError(' [x] Unknown amp_dtype: ' + args.train.amp_dtype)
saver.log_info("epoch|batch_idx/num_batches|output_dir|batch/s|lr|time|step")
for epoch in range(args.train.epochs):
for epoch in range(start_epoch, args.train.epochs):
for batch_idx, data in enumerate(loader_train):
saver.global_step_increment()
optimizer.zero_grad()
Expand Down
2 changes: 1 addition & 1 deletion diffusion/unit2mel.py
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@
class DotDict(dict):
def __getattr__(*args):
val = dict.get(*args)
return DotDict(val) if type(val) is dict else val
return DotDict(val) if type(val) is dict else val # noqa: E721

__setattr__ = dict.__setitem__
__delattr__ = dict.__delitem__
Expand Down

0 comments on commit 68802ec

Please sign in to comment.