Cool_Tools/Retrieval-based-Voice-Conversion-WebUI
1
0
Fork 0
mirror of synced 2025-02-21 04:46:57 +01:00
Code Releases Wiki Activity

Update train_nsf_sim_cache_sid_load_pretrain.py

Browse Source
This commit is contained in:
liujing04 2023-04-09 15:26:05 +00:00 committed by GitHub
parent 27c7e3f6a3
commit 38539e3c07
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
train_nsf_sim_cache_sid_load_pretrain.py
View File

@ -68,7 +68,7 @@ def run(rank, n_gpus, hps):
else:train_dataset = TextAudioLoader(hps.data.training_files, hps.data)
train_sampler = DistributedBucketSampler(
train_dataset,
hps.train.batch_size,
hps.train.batch_size*n_gpus,
# [100, 200, 300, 400, 500, 600, 700, 800, 900, 1000, 1200,1400], # 16s
[100, 200, 300, 400, 500, 600, 700, 800, 900], # 16s
num_replicas=n_gpus,