rixty/VoiceCraft
1
0
Fork 0
mirror of https://github.com/jasonppy/VoiceCraft.git synced 2025-06-05 21:49:11 +02:00
Code Issues Packages Projects Releases Wiki Activity

revised env setup, random seed effective

Browse Source
This commit is contained in:
jason-on-salt-a40
2024-03-31 13:50:20 -07:00
parent 2f78e8d435
commit 991b1fe3bb
3 changed files with 35 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
inference_speech_editing.ipynb
View File

@@ -30,13 +30,15 @@
"# import libs\n",
"import torch\n",
"import torchaudio\n",
"import numpy as np\n",
"import random\n",
"\n",
"from data.tokenizer import (\n",
" AudioTokenizer,\n",
" TextTokenizer,\n",
")\n",
"\n",
"from models import voicecraft\n"
"from models import voicecraft"
]
},
{
@@ -72,6 +74,15 @@
"silence_tokens = [1388,1898,131] # if there are long silence in the generated audio, reduce the stop_repetition to 3, 2 or even 1\n",
"stop_repetition = -1 # -1 means do not adjust prob of silence tokens. if there are long silence or unnaturally strecthed words, increase sample_batch_size to 2, 3 or even 4\n",
"# what this will do to the model is that the model will run sample_batch_size examples of the same audio, and pick the one that's the shortest\n",
"def seed_everything(seed):\n",
" os.environ['PYTHONHASHSEED'] = str(seed)\n",
" random.seed(seed)\n",
" np.random.seed(seed)\n",
" torch.manual_seed(seed)\n",
" torch.cuda.manual_seed(seed)\n",
" torch.backends.cudnn.benchmark = False\n",
" torch.backends.cudnn.deterministic = True\n",
"seed_everything(seed)\n",
"device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n",
"\n",
"# point to the original file or record the file\n",