-
I really want to use PWGAN for hifi-singer. Since there is no direction in .md file, little confuse how should I prepare dataset. Could you please describe how to compile and dataset in detail? If you…
-
I've downloaded the file @ https://drive.google.com/drive/folders/1rmeW24lrCg_qwPkVI0D4bRNq4HSv_4rE
but can't manage to get the model to load, on either the master branch or the v1.0.0 zip file.
I…
-
Hi,
First of all, thanks for this incredible work, I hope to be able to contribute soon !
I'm trying to finetune VITS using espeak VCTK 44100 version, but after 245 epochs, the generated audio h…
-
I'm getting this error on a relatively low-powered system I'm using for testing:
RuntimeError: CUDA out of memory. Tried to allocate 20.00 MiB (GPU 0; 4.00 GiB total capacity; 2.80 GiB already alloca…
-
Hi ,
Could you share with me about your Gen Loss and Mel-Spec Error when you got the final model?
I'm trying to train on another dataset for around 3 days and I see loss, error decrease but the qua…
-
I want to use FastSpeech 2 + hifigan, but it sound a little nosie in some generated audios, so I get the generate mel-spectrogram from FastSpeech 2 to retrain the hifigan, BUT MEET the error when fine…
-
- News
- [Facebook has gone~ Meta has come!!!!](https://news.naver.com/main/read.naver?mode=LSD&mid=sec&sid1=101&oid=015&aid=0004622175)
- [State of AI Report 2021](https://www.stateof.ai/)
![…
-
我租了一台8个GPU、单GPU 84G显存的tesla 100，使用缺省头像生成是没问题的。如果使用自动定义头像（我自己的照片，7MB），创建虚拟角色的步骤没有问题（就是生成这个me.mp4)，但在生成demo video的时候失败了，报CUDNN_STATUS_NOT_SUPPORTED
# python general_demo.py --human ./file/input/m…
-
- AI News
- ICCV notification out: accept letter 받으신 모든 분들 축하드립니다!
- IBM Watson 의 현주소
- NYT: https://www.nytimes.com/2021/07/16/technology/what-happened-ibm-watson.html
- 국내: https://…
-
I saw “please set to 8000 for HiFi-GAN vocoder, set to null for MelGAN vocoder” about mel_fmax in preprocess.yaml
But I didnt change it when using MelGAN, it seems not bad.
Why mel_fmax is different…