Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

update config.json

This commit is contained in:
erogol 2020-05-20 11:55:32 +02:00
parent 97cd39bf99
commit dc166b42e3
2 changed files with 9 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
config.json
View File

@ -34,7 +34,7 @@
"signal_norm": true, // normalize spec values. Mean-Var normalization if 'stats_path' is defined otherwise range normalization defined by the other params. "signal_norm": true, // normalize spec values. Mean-Var normalization if 'stats_path' is defined otherwise range normalization defined by the other params.
"min_level_db": -100, // lower bound for normalization "min_level_db": -100, // lower bound for normalization
"symmetric_norm": true, // move normalization to range [-1, 1] "symmetric_norm": true, // move normalization to range [-1, 1]
"max_norm": 1.0, // scale normalization to range [-max_norm, max_norm] or [0, max_norm] "max_norm": 4.0, // scale normalization to range [-max_norm, max_norm] or [0, max_norm]
"clip_norm": true, // clip normalized values into the range. "clip_norm": true, // clip normalized values into the range.
"stats_path": null // DO NOT USE WITH MULTI_SPEAKER MODEL. scaler stats file computed by 'compute_statistics.py'. If it is defined, mean-std based notmalization is used and other normalization params are ignored "stats_path": null // DO NOT USE WITH MULTI_SPEAKER MODEL. scaler stats file computed by 'compute_statistics.py'. If it is defined, mean-std based notmalization is used and other normalization params are ignored
}, },

2
utils/training.py
View File

@ -9,7 +9,7 @@ def check_update(model, grad_clip, ignore_stopnet=False):
grad_norm = torch.nn.utils.clip_grad_norm_([param for name, param in model.named_parameters() if 'stopnet' not in name], grad_clip) grad_norm = torch.nn.utils.clip_grad_norm_([param for name, param in model.named_parameters() if 'stopnet' not in name], grad_clip)
else: else:
grad_norm = torch.nn.utils.clip_grad_norm_(model.parameters(), grad_clip) grad_norm = torch.nn.utils.clip_grad_norm_(model.parameters(), grad_clip)
if np.isinf(grad_norm): if torch.isinf(grad_norm):
print(" | > Gradient is INF !!") print(" | > Gradient is INF !!")
skip_flag = True skip_flag = True
return grad_norm, skip_flag return grad_norm, skip_flag