azalea/VITS-fast-fine-tuning
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/main'

Browse Source
This commit is contained in:
Plachta
2023-06-14 15:36:59 +08:00
parent 9cd6f36696 e97b185188
commit 809232f8d8
1 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
LOCAL.md
+5 -5
View File
@@ -24,7 +24,7 @@
```
6. Download auxiliary data for training
```
!mkdir pretrained_models
mkdir pretrained_models
# download data for fine-tuning
wget https://huggingface.co/datasets/Plachta/sampled_audio4ft/resolve/main/sampled_audio4ft_v2.zip
unzip sampled_audio4ft_v2.zip
@@ -94,13 +94,13 @@
If not, run `python3.8 preprocess_v2.py --languages "{PRETRAINED_MODEL}"`
Do replace `"{PRETRAINED_MODEL}"` with one of `{CJ, CJE, C}` according to your previous model choice.
11. Start Training.
Run `python finetune_speaker_v2.py -m "./OUTPUT_MODEL" --max_epochs "{Maximum_epochs}" --drop_speaker_embed True`
Run `python finetune_speaker_v2.py -m ./OUTPUT_MODEL --max_epochs "{Maximum_epochs}" --drop_speaker_embed True`
Do replace `{Maximum_epochs}` with your desired number of epochs. Empirically, 100 or more is recommended.
To continue training on previous checkpoint, change the training command to: `python finetune_speaker_v2.py -m "./OUTPUT_MODEL" --max_epochs "{Maximum_epochs}" --drop_speaker_embed True --cont True`. Before you do this, make sure you have previous `G_latest.pth` and `D_latest.pth` under `./OUTPUT_MODEL/` directory.
To view training progress, open a new terminal and `cd` to the project root directory, run `tensorboard --logdir="./OUTPUT_MODEL"`, then visit `localhost:6006` with your web browser.
To continue training on previous checkpoint, change the training command to: `python finetune_speaker_v2.py -m ./OUTPUT_MODEL --max_epochs "{Maximum_epochs}" --drop_speaker_embed True --cont True`. Before you do this, make sure you have previous `G_latest.pth` and `D_latest.pth` under `./OUTPUT_MODEL/` directory.
To view training progress, open a new terminal and `cd` to the project root directory, run `tensorboard --logdir=./OUTPUT_MODEL`, then visit `localhost:6006` with your web browser.
12. After training is completed, you can use your model by running:
`python VC_inference.py --model_dir ./OUTPUT_MODEL/G_latest.pth --share True`
13. To clear all audio data, run:
```
rm -rf ./custom_character_voice/* ./video_data/* ./raw_audio/* ./denoised_audio/* ./segmented_character_voice/* long_character_anno.txt short_character_anno.txt
```
```