-
## š Description
### To Reproduce
```bash
$ CUDA_VISIBLE_DEVICES=0 python3 TTS/recipes/ljspeech/hifigan/train_hifigan.py
```
```python
# train_hifigan.py
import os
from trainer iā¦
-
Hi, Nemo Developer:
Happy new year first.
**Describe the bug**
I am trying to have a trial on voice clone. So I am trying to finetune a TTS model based on a test person's voice clips. Have sā¦
-
-
Related to **Fastpitch/Triton client feature implementation**
I have followed your Faspitch [triton](https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/SpeechSynthesis/FastPitch/trā¦
-
**Describe the bug**
Using the main branch of Nemo and TTS inference with Fastpitch and Hifigan / German single speaker model results in bad audio.
**Steps/Code to reproduce bug**
git clonā¦
-
Hi Florian. I just read your paper on EXACT PROSODY CLONING IN ZERO-SHOT MULTISPEAKER TEXT-TO-SPEECH(https://arxiv.org/pdf/2206.12229.pdf). Great job. Very interesting contributions, thanks for sharinā¦
-
**Describe the bug**
German fastpitch model refers to non existing tokenizer
**Steps/Code to reproduce bug**
git clone https://github.com/NVIDIA/NeMo/
cd NeMo
python3.8 -m venv venv
sourceā¦
-
Hello! Do you think it's possible to incorporate automatic aligner as in FastPitch (https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/SpeechSynthesis/FastPitch), as described in paperā¦
-
Related to **FastPitch1.1/PyTorch**
**Describe the bug**
The training is broken by "loss is NaN", As FastPitch loss function is compused by mel_loss, duration loss, pitch loss, energy loss andā¦
-
### Describe the bug
After downloading VCTK dataset at the appropriate location, when running default training pipeline for vctk / fastpitch, no pitch information is computed and saved in f0_cache piā¦