-
Sample RNN has been published, which seems that tiered rnn outperforms conv stacks.
http://www.gitxiv.com/posts/kQhs4N6rRohXDcp89/samplernn-an-unconditional-end-to-end-neural-audio
https://github.…
-
https://pan.baidu.com/s/1pu_XfQJnLRcQZYfawqCeNQ ，提取码：7777
aishell3数据集，Tesla V100 32G，BS 96训练的160K，loss值0.24
同时本人有两台V100 32G闲置，为BUG时撸的云服务器，有想训练啥的也可以提要求，反正闲着也是闲着。
-
Hi all.
_This project is very interesting, and I'd like to create a french voice for ubuntu (ubuntu is very poor in french male TTS_)
- how many wav sentences do I need to create correct voice ?
…
-
### Describe the bug
If a sentence too long (separate by comma) some part of it will missing during the audio generation
Example:
On April 1, 1942, Desmond Doss joined the United States Army. Li…
-
I saw the Dockerfile and it automatically downloads the newest version of Tensorflow.
Recently, Tensorflow revealed 2.0 version and it's quiet different from the older version.
Could you let me know…
-
Hey, I saw you are taking mel start /end val 4,-4 now i think its 0.5/-0.5. You are normalizing mel spectrogram in range -4 to +4 then dont you think using above token values will cause problems??
…
-
After @jyegerlehner 's implement of global condition #168 , I would like to ask which features of the model we should focus for now, and which approach we should do for each. Here there are some optio…
-
Hello @A-Jacobson.
Great work with your implementation and more importantly with you clear representation of the model in your README (100% better that the one presented in the paper x) ).
So I …
-
### Describe the bug
Model `tts_models/fr/mai/tacotron2-DDC`
Error:
```
> Model input: hello
> Speaker Idx:
> Language Idx:
> Text splitted to sentences.
['hello']
ERROR:server:Except…
-
```I was training Tacotron-2 model by first training tacotron model, then wavenet model. When I run synthesis.py for wavenet model I'm getting the error message below.
Traceback (most recent call las…