-
I tried to export a FastPitch model I trained to ONNX with [export.py](https://github.com/NVIDIA/NeMo/blob/main/scripts/export.py).
The command I used was:
`python scripts/export.py "/home/xxx/TTSs/…
-
Hi guys,
I am trying to train an ASR with nemo. I preprocessed data as shown on the tutorial. but when I tried to train the model, I have the following error : AttributeError: Can't pickle local obj…
-
**Describe the bug**
I'm trying to finetuning HiFiGAN using this lib, using WSL2 I could start training process, but it will stuck at random step.
**Steps/Code to reproduce bug**
Running prom…
-
I'm using fastpich & univnet from Nemo to generate audio from text (TTS). I want to have the time information of each word in such a way that it shows in what period of time each word was uttered. The…
-
Hello, I am using the FastPitch along with the HiFi-GAN as the vocoder using GPU. The training is done quite fast using multiple gpus, however, the inference is incredibly slow. It is taking hours to …
-
trtexec --onnx=speech2phone.onnx --minShapes=input:1x32x80 --optShapes=input:1x64x80 --maxShapes=input:1x128x80 --saveEngine=speech2phone.engine --workspace=1024 --best
onnx model:https://drive.goo…
-
### Describe the bug
tts/vctk/fastpitch cannot be paired with other vocoders, but there's no documentation specifying which vocoder is the default vocoder.
### To Reproduce
N/A
### Expected behavi…
-
**Describe the bug**
When I stopped fine-tuning the FastPitch model and wanted to restart training, I noticed it checks for the last checkpoint in the wrong directory (I'm settings the checkpoints …
-
-
**Describe the bug**
The RTF for interference is greather than 2 on Intel CPUs.
**Steps/Code to reproduce bug**
The below code produces a 7 second audio (speech2.wav) after properly loading …