-
I have another problem that I try to match tacotron2 [https://github.com/begeekmyfriend/tacotron2](url) ,but the generated audio only have noise.
The TTS params is already match diffwave, i found th…
-
Hi
I am trying to train a model for text to speech in German.. I Have been able to train the model using espeak-ng backend, but at inference time I cant get the model to do inference. I am using A…
-
-
Hi Thorsten,
fist of all thanks for the nice dataset. Out of curiosity I was training a FastPitch model on it using my repo: https://github.com/as-ideas/ForwardTacotron
Here is a sample vocoded…
-
Hello,
I am training a Tacotron2 model with my custom dataset in Hindi.
Dataset Details: 25 hours of data, 22 KHz, 16 bit, Single Female Speaker
Issue: The training is very slow, and the loss s…
-
Hi
I am using 4GPUs for training TTS model and I have 24G ram on each GPU.
To speech up the process I changed the number of batch bins from 5120000 to 20400000 however, I didnt gain any speed!
…
-
**Describe the bug**
[edited]
When running inference twice in the colab, different results are obtained. I am aware that one can use a manual seed https://github.com/espnet/espnet/issues/2647
…
-
这里是免费的程序员招聘服务。
如果你们团队正在招人，欢迎把招聘信息发在这个帖子里面。请简要描述，岗位名称、工作地点、岗位要求、团队简介、联系方式等等。
**注意：同一个团队如果招聘多个岗位，请写在一起，不要分成多个部分张贴。**
读者可以咨询，但请不要发布与招聘无关的内容，禁止对公司或岗位进行评论或抱怨。如果有意应聘，请直接与发帖人联系。
谢绝中介和猎头发帖，违者拉黑。
…
-
### Describe the bug
Failes to output anything. Using python 3.10.5 on Gentoo and tried installing from pip and locally.
Command: tts --text "this is a test" --out_path /tmp/outtest.wav
### To Re…
-
### Describe the bug
I'm trying to run Tacotron2 training, but receives `RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!`
### To Reprod…