-
Hello, how can I test the loss accuracy of a checkpoint trained with FastPitch?
Also, if I train FastPitch, is it also necessary to train WaveGlow for the entire end-to-end to work?
Thanks.
-
I would like to prepare dataset, i.e., pitch estimation, for FastPitch-1.1 training when the sample rate of audio is 8 kHz.
However, I am getting the following assertion error from fastpitch/data_fun…
-
Hi there,
Great work!
I have moved to the latest fastpitch with the internal alignment model (which works great), but it is rather slow.
Of course in the old model, I was passing my own ground …
-
Hello,
I am training a model in TalkNet. Before start training the spectrogram I created the durations.pt and f0s.pt
After that I started training the spectrogram with talknet_spect.py from exam…
-
Hi. Your fastpitch makes me very happy. However, I got a problem. I was not happy with the mels I get. I read that I can use dur_tgt to do more accurate mels. But I don't understand how to get them. C…
-
Hi all.
The tutorial https://github.com/NVIDIA/NeMo/blob/main/tutorials/tts/FastPitch_Finetuning.ipynb does not work from scratch.
First, I have to replace NeMo for NVIDIA in the first setup ce…
-
Hey, it would be very cool if there were classes already developed for carrying out Text2Speech tasks. We do have many classes capable of doing Speech2Text, but for the opposite task there are no tran…
-
**Describe the bug**
Pyini (and probably some other things) are missing when running in a Colob environment.
**Steps/Code to reproduce bug**
Run FastPitch_Finetuning.ipynb on a Colab instance.
…
-
**Describe the bug**
I try to export fast pitch models, but it took a lot of RAM then process is killed. In my case, I use Mac OS to export and swap increase from 3 GB to 54 GB. I also used to try …
-
Hello! I'm trying to fine-tune the HiFi according to your fastpitch_finetuning tutorial. I generated manifests in the same format as in the example. Then I launched the fine-tuning script by simply ch…