-
### Describe the bug
When trying to synthesize speech using python:
`tts = TTS("tts_models/en/ljspeech/tacotron2-DDC")`
It crashes python.
When running
`tts --text "Hello this is a test." -…
-
大佬您好，我最近在用tacotron2训练命运石之门中助手的语音模型，然后想用您写的软件转换成语音输出，可是在运行过程中产生了如下报错
然后我又下载了您提供的Atri的文件试着跑了一遍，发现也产生了同样的报错
请问如何解决这种情况呢？
报错如下：
Exception in Tkinter callback
Traceback (most recent call last):
…
-
Hi, I'm trying to use a Japanese dataset.
I made the filelist look like this:
`dataset/ang/wav/angry-0.wav|Kimurasan wa watashi ni shashin wo misete kuremashita.`
`dataset/ang/wav/angry-1.wav|Tero …
-
hello，how can i change mel channels from 80 to 100 to use your model？
-
Related to **Model/Framework(s) or something else (describe)**
*Examples:*
* *GNMT/PyTorch*
* *AMP*
* *Tensorflow 2.0*
* *Jupyter notebooks*
**Is your feature request related to a proble…
-
TorchBench CI has detected a performance signal or runtime regression.
Base PyTorch commit: 61239df555df02e8c60a2ad63363878a2a57c161
Affected PyTorch commit: 61239df555df02e8c60a2ad63363878a2a57c16…
-
麻烦看看这是什么问题 谢谢
-
Hi,
I have been able to set up speechbrain on my linux server. And I am currently training the Text-to-Speech Tacotron2 and HifiGAN. However, I would really like to use transfer learning instead of…
-
### Describe the bug
Looking at Capacitron tests to understand behavior and noticed the unit test fails with
"tensors to be on the same device, but found at least two devices, cuda:0 and cpu!"
C…
-
I trained korean tacotron2 at 468K using kss data and my custom data.
And I made a wave result with mb-melgan.
The result is great, but it has noise like any machine sound.
One of machine sound t…