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

load mel features if 'feature_path' is provided

This commit is contained in:
erogol 2020-06-15 11:28:27 +02:00
parent 3c20afa1c9
commit 98fd3b53f2
2 changed files with 7 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vocoder/configs/multiband_melgan_config.json
View File

@ -111,7 +111,7 @@
// OPTIMIZER
"noam_schedule": false, // use noam warmup and lr schedule.
"warmup_steps_gen": 4000, // Noam decay steps to increase the learning rate from 0 to "lr"
"warmup_steps_disc": 4000,
"warmup_steps_disc": 4000, // Noam decay steps to increase the learning rate from 0 to "lr"
"epochs": 10000, // total number of epochs to train.
"wd": 0.0, // Weight decay weight.
"gen_clip_grad": -1, // Generator gradient clipping threshold. Apply gradient clipping if > 0

7
vocoder/train.py
View File

@ -441,7 +441,12 @@ def evaluate(model_G, criterion_G, model_D, criterion_D, ap, global_step, epoch)
def main(args): # pylint: disable=redefined-outer-name
# pylint: disable=global-variable-undefined
global train_data, eval_data
eval_data, train_data = load_wav_data(c.data_path, c.eval_split_size)
print(f" > Loading wavs from: {c.data_path}")
if c.feature_path is not None:
print(f" > Loading features from: {c.feature_path}")
eval_data, train_data = load_wav_feat_data(c.data_path, c.feature_path, c.eval_split_size)
else:
eval_data, train_data = load_wav_data(c.data_path, c.eval_split_size)
# setup audio processor
ap = AudioProcessor(**c.audio)