-
How FastSpeech2 export onnx ? I want to export onnx format and export tflite to deploy.
-
设备明明有空间，但是显示内存不足。
修改了trainpy上的device = torch.device("cuda:1" if torch.cuda.is_available() else "cpu")，指定使用第二个GPU，但是他还是用的第一个
(FastSpeech) gaoyiyao@deeplearning-Z10PE-D8-WS:/home_1/gaoyiyao/FastSpeech…
-
From the paper, it seems like a FastSpeech2 model was trained end-to-end in combination with the diffusion vocoder. Are you planning on releasing its weights as well?
This would be a super nice ad…
-
yaml文件如下：
# This is the parameter configuration file for streaming tts server.
#################################################################################
# SERV…
-
Hello , I am facing a problem with creating a model for TTS. These are the below error showing at stage 6 . Kindly let me know the reason of issue.
hs shape: torch.Size([15, 110, 384])
p_embs shap…
-
As of https://github.com/roedoejet/FastSpeech2_lightning/pull/20, error messages were changed to print statements, but pending a longer discussion of whether to use print statements or logger.error, t…
-
Hi, my name is Yoonhyung Lee, who is studying Text-to-Speech.
Thank you for your nice implementation of FastSpeech2.
It helped me a lot to study it, but a question occurred to me.
According to th…
-
The pitch and energy bins are determined based on the `stats.json` of a particular dataset, which will change during fine-tuning. Currently the bins will change and the model has to adapt and learn ho…
-
raceback (most recent call last): | 6/1367 [00:06
-
目前测试下来mb_melgan_csmsc的推理速度满足离线环境下CPU实时推理，其他的VOC模型都太慢，但是我用fastspeech2_mix微调克隆了一个男生音色后，使用mb_melgan_csmsc推理音色就不对，只能使用aishell3数据集训练的VOC模型，而mb_melgan只有csmsc数据集训练的模型，问题来了，如何使用aishell3数据训练一个mb_melgan模型，求指点