Labmem-Zhouyx/CDFSE_FastSpeech2
The Official Implementation of “Content-Dependent Fine-Grained Speaker Embedding for Zero-Shot Speaker Adaptation in Text-to-Speech Synthesis”
PythonMIT
Issues
- 1
preprocess.py
#14 opened by gaoyiyao - 0
- 0
请问有预训练模型可以使用吗?
#12 opened by dthcle - 1
LibriTTS的fastspeech2 pretrained model在哪里下载呢?
#7 opened by Nueve879 - 1
请问代码有 切片、打乱、重组的操作吗? 这部分代码在哪里呀
#11 opened by tuntun990606 - 1
After training, PhnCls Loss and SpkCls Loss do not decay. Reasoning timbre is not the same
#3 opened by Summerxu86 - 0
这个版本的代码经过十几次训练测试,无法正确训练出结果
#10 opened by yyz845935161 - 3
你好,关于AIshell3数据的训练问题
#5 opened by 1319224734 - 0
T-SNE Drawing
#9 opened by freshwindy - 0
hifigan训练参数
#8 opened by Sunshine1088 - 0
请问需要多少说话人训练泛化性很好?
#6 opened by Pydataman - 5
关于libriTTS数据集
#4 opened by WhiteFu - 5
What normal losses value should be
#1 opened by josh-zhu - 2
Speaker predict training problem
#2 opened by 980202006