Issues
- 15
中文模型有人训练成功的吗?
#30 opened by wildBigPanda - 9
1500条英文语音训练了1000epoch,合成后是莫名其妙的英文语句
#32 opened by zhanglina94 - 0
nene数据集是从哪里获取的呀?
#38 opened by zhaojingxin123 - 16
训练esd中文数据,接近700个epoch后,合成的语音依旧是听不清内容。
#36 opened by alittlenico - 1
初始化阶段不装载netD权重是有什么玄机?还是笔误啊
#37 opened by is - 2
请问现在支持中文吗?
#19 opened by Candlend - 10
2000条语音训练了2000个迭代,但是合成不了语音,一点声音都没有,可能是什么原因?
#22 opened by jmaxzh - 1
谁有好的中文情绪音频数据集啊
#31 opened by tppqt - 6
感谢提供,请问如何同时支持中文和英文
#20 opened by 40740 - 0
inputs变量为空
#35 opened by alittlenico - 0
Multiple GPU training bug
#34 opened by RK-BAKU - 0
- 1
IndexError: Dimension out of range
#27 opened by beanels01 - 1
- 0
- 4
报错:RuntimeError: Given groups=1, weight of size [512, 1, 10], expected input[1, 182741, 1] to have 1 channels, but got 182741 channels instead
#25 opened by Justsenger - 1
- 1
使用中文模型,是不是只需要更换pth文件即可呀?
#26 opened by HildaM - 0
wav2vec 模型是针对英文的?
#23 opened by dailygoing - 1
有没有类似于 洛天依 的库
#11 opened by leeseean - 0
- 0
运行train_ms.py后报ValueError错
#18 opened by ecchiaru114514 - 3
编码错误
#6 opened by signupbook - 0
读取检查点部分写错了
#17 opened by chriscainx - 0
单人数据集需要多少时长,训练多少epoch才有比较好的效果呢?
#16 opened by cloudew - 0
训练情感,音频应该要什么样的?
#15 opened by erikaemma - 0
- 0
emotion_extract sample rate must 16000
#13 opened by yuisunn - 0
已自己解决 tts is not defined
#12 opened by EsawaAzusa - 0
up可以支持一下中文吗球球
#10 opened by lucasjinreal - 0
Can not load from the checkpoint
#9 opened by Luke9086 - 1
defective codes at the latest commit
#7 opened by azulika - 0
Original Checkpoints
#5 opened by ArEnSc - 0
数据集
#4 opened by signupbook