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

upload files

Browse Source
This commit is contained in:
Plachta
2023-02-16 17:41:23 +08:00
parent eed75db80d
commit 3a6bf5adbb
3 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
finetune_speaker.py
+1 -1
View File
@@ -150,7 +150,7 @@ def train_and_evaluate(rank, epoch, hps, nets, optims, schedulers, scaler, loade
net_g.train() net_g.train()
net_d.train() net_d.train()
for batch_idx, (x, x_lengths, spec, spec_lengths, y, y_lengths, speakers) in enumerate(train_loader): for batch_idx, (x, x_lengths, spec, spec_lengths, y, y_lengths, speakers) in enumerate(tqdm(train_loader)):
x, x_lengths = x.cuda(rank, non_blocking=True), x_lengths.cuda(rank, non_blocking=True) x, x_lengths = x.cuda(rank, non_blocking=True), x_lengths.cuda(rank, non_blocking=True)
spec, spec_lengths = spec.cuda(rank, non_blocking=True), spec_lengths.cuda(rank, non_blocking=True) spec, spec_lengths = spec.cuda(rank, non_blocking=True), spec_lengths.cuda(rank, non_blocking=True)
y, y_lengths = y.cuda(rank, non_blocking=True), y_lengths.cuda(rank, non_blocking=True) y, y_lengths = y.cuda(rank, non_blocking=True), y_lengths.cuda(rank, non_blocking=True)
utils.py
+1 -1
View File
@@ -152,7 +152,7 @@ def get_hparams(init=True):
help='JSON file for configuration') help='JSON file for configuration')
parser.add_argument('-m', '--model', type=str, default="pretrained_models", parser.add_argument('-m', '--model', type=str, default="pretrained_models",
help='Model name') help='Model name')
parser.add_argument('-n', '--max_epochs', type=int, default="50", parser.add_argument('-n', '--max_epochs', type=int, default=50,
help='finetune epochs') help='finetune epochs')
args = parser.parse_args() args = parser.parse_args()
whisper_transcribe.py
+1 -1
View File
@@ -81,7 +81,7 @@ if __name__ == "__main__":
with open("./configs/finetune_speaker.json", 'r', encoding='utf-8') as f: with open("./configs/finetune_speaker.json", 'r', encoding='utf-8') as f:
hps = json.load(f) hps = json.load(f)
# modify n_speakers # modify n_speakers
hps['data']["n_speakers"] = 999 + len(speaker2id) hps['data']["n_speakers"] = 1000 + len(speaker2id)
# add speaker names # add speaker names
for speaker in speaker_names: for speaker in speaker_names:
hps['speakers'][speaker] = speaker2id[speaker] hps['speakers'][speaker] = speaker2id[speaker]