-
**Describe the bug**
When I was trying to train Fastpitch from scratch using `fastpitch_align_v1.05.yaml` config, after it spending over 1 hour trying to `Loading dataset`, it threw the error:
```…
-
Hello. I'm trying to train new FastPitch model from scratch for another language and I've noticed that during warmup steps learning rate first increases from 3.16e-06 to around 2.70e-03 than starts de…
-
It's not an issue, just question.
I adapted FastPitch training to polish changing few files, extending symbols, changing cleaners, etc.
Now when a training started I can see my model file is over 50…
-
**Describe the bug**
When I tried to train / finetune FastPitch, the following error shows up:
```
Traceback (most recent call last):
File "/root/miniconda3/lib/python3.8/site-packages/pytor…
-
The vocoder model designated for the VCTK FastPitch model is not compatible and it produces pure noise.
We need to train a new compatible vocoder or update the FastPitch model.
Until then recom…
-
**Describe the bug**
Do Nemo TTS models train from pre-trained model?
Command is blow
python tacotron2.py train_dataset=filelists/transcript_train.json validation_datasets=filelists/transcrip…
-
## 🐛 Description
I'm running training based on the recipe provided in the repository, but I'm having trouble showing the sample spectogram image generated during training and the sample audio o…
-
**Describe the bug**
Trying to run tts/tutorials/fastpitch_finetune.ipynb from Colab, the first cell give the following error:
`Collecting nemo_toolkit[tts]
Cloning https://github.com/NeMo/Ne…
-
### News
- Conferences
- CVPR 2022: 6.19 ~ 24 (New Orleans)
- 대기업 중심의 AI 투자 관련 (SK, LG, KT 등등)
- [스캐터랩, 정부와 AI 윤리점검표 개발 추진](https://n.news.naver.com/mnews/article/092/0002259047?sid=105)
### …
-
I'd like to train my own TTS model in Italian, using the portion of the MAILABS dataset (~18 hours). If I train the Tacotron 2 model with this dataset (16 kHz) can I fine tune from a pre-existing Engl…