godspirit00

Runtime error when exporting FastPitch model to ONNX

4

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/Nemo-models/nancy_fastpitch-44k-new-v3.nemo" "nancy_fastpitch-44k-new-v3.onnx" --runtime-check --device="cpu" --autocast` But it produced an error:...

Finetuning a Grad-TTS model on a small dataset?

2

Hi! Thanks for the great work! I have a small dataset of ~2 hours. How do I finetune a Grad-TTS model on it? Thanks!

Is it possible to control the speed of speech?

1

Thanks for the great work! I wonder if it is possible to control the speed of the output speech?

Hi, I am training a model on the ryanspeech dataset. Currently it is on 125k+ steps, and I tried to synthesize a speech with the checkpoint, but the result is...

[HIFIGAN] How to train a model of 44100 sampling rate?

1

I tried to set the related arguments in `train.py` as `--sampling_rate 44100 --filter_length 2048 --hop_length 512 --win_length 2048`, but got the following error: ``` train.py:412: UserWarning: Using a target size...

SLM Adversarial Training did not start when finetuning

13

I tried to do finetuning on a small dataset with 2 speakers. I set `epochs=25`, `diff_epoch=8`, `joint_epoch=15`. The Style Diffusion training started as expected, but SLM Adversarial Training never started...

Is it possible to control the speed of the speech?

2

Hi! Thanks for the great work! I have a question: is it possible to control the speed of the speech, like Fastspeech2, VITS, and so forth? Thanks!

求问微调/Finetuning？

20

大佬好，我的一个数据集只有约为1000条样本，1小时20分钟，请问怎么在现有模型上微调？多谢！