-
I found your repo from this issue: https://github.com/jik876/hifi-gan/issues/63
I am still confused about the mismatch between repos in Mel spectrogram generation. I collect some method from some T…
-
Hi, I want to know what config does you use when you train the hifigan model of DataBaker to get the samples in the webset https://light1726.github.io/vaenar-tts/.
With these parameters clearifie…
-
Dear,
Thank you for your great works.
I followed the procedure to train our TTS by the fs2 + hifigan joint training approach using the corresponding pretrained models with the config provided in …
-
[HiFiGan](https://github.com/jik876/hifi-gan) has sota results in wav generation from mel spectrograms
Is it possibile to add support to `hifigan` model, after the `mel` generation, in order to…
-
Hi, thanks for sharing the code, it is well appreciated. Some questions:
- Do you train with mean-var normalization? If not, what is the range normalization?
- I tried to plug in the models using …
-
Hi,
I recently discovered in experiments that the audio generated using fluentspeech is also different from the original audio in the non-modified parts. Here are the waveforms of the unmodified port…
-
i removed the postnet(remove the code of model and loss about postnet ) and set the pitch_quantization="log",set features of pitch and enery = "frame_level", normalization="False",and other configurat…
-
I'm interested in training to convert 24 kHz mel spectrograms to 48 kHz waveforms (like HIFI-GAN2). Might not work without changing the architecture, but that's ok. How would you modify the config fil…
-
Got this with your trained model:
```
Traceback (most recent call last):
File "inference.py", line 60, in
main(args)
File "inference.py", line 23, in main
model.load_state_dict(che…
ghost updated
3 years ago
-
https://github.com/jik876/hifi-gan/blob/4769534d45265d52a904b850da5a622601885777/models.py#L81
Hi, why is 80 hardcoded here? Should it match [num_mels](https://github.com/jik876/hifi-gan/blob/47695…
bzp83 updated
2 months ago