-
I am using a recipe to create a new multi-speaker model and while trying to train, it dies after one epoch with this warning:
This overload of addcmul_ is deprecated: addcmul_(Number value, Tensor t…
-
Hello @kan-bayashi I can see gan_tts task now work with joint TTS training but wondering if you have example for specify pretrained models, switching vocoder impl and expected training time difference…
-
Hi @jik876 @Edresson
I have been trying to integrate tacotron2 and Hifi gan to create fully end to end TTS. But when I am feeding Tacotron2 output to your finetuned model of HiFi GAN output audio …
-
Hi,
I have trained a WaveGlow Vocoder with my own data corpus. I also trained a TTS model (ESPnet FastSpeech2) using the same corpus. As the Mel params differ, I get pure noise outputs. I need to kno…
-
The log message and config file are shown in the following:
```
/home/notebook/code/personal/ParallelWaveGAN/parallel_wavegan/losses/mel_loss.py:164: UserWarning: Using a target size (torch.Size([…
-
Hi, I trained duration extractor and speedyspeech with my own dataset which is korean single speech dataset
(RIFF (little-endian) data, WAVE audio, Microsoft PCM, 16 bit, mono 22050 Hz)
I just chang…
-
Hi,
I have tried training with the current default config and it drops the learning rate too fast and the model converges to generate noise. Because when `scheduler_after_epoch=False`, `Exponential…
-
Hi,
I have trained a vocoder model using parallel_wavegan on my own corpus and wondering if I can upload it just like TTS models (tacotron, fastspeech, etc) to huggingface and then use the ```vocoder…
-
macOS（GPUはない環境です）
Python 3.9.4
## 再現手順
```
$ pip install ttslearn
$ python
>>> from ttslearn.dnntts import DNNTTS
Traceback (most recent call last):
File "", line 1, in
File "/Users/…
-
使用 AIshell3 训练合成器，效果如下：
与第三方TTS效果对比：
![test](https://user-images.git…