-
Instruction step by step how to install and train Tacotron2
-
We need to replace the current fishspeech with better TTS model.
WIP Shortlist of Possible candidates:
- Amphion (https://github.com/open-mmlab/Amphion)
-
**Describe your question**
I am training a TTS model using Fastspech2. I started training my model about 6 hours ago (40,000~ steps) and loss rate dropped from `4~` down to `0.8~`. I tried running …
-
## Fix the model test for `tacotron2.py`
1. setup env according to [Run a model under torch_xla2](https://github.com/pytorch/xla/blob/master/experimental/torch_xla2/docs/support_a_new_model.md)
2.…
-
I was trying to access the drive of the tacotron2 model but it says: permission denied
-
Repro:
```
python benchmarks/dynamo/torchbench.py --accuracy --inference --amp --backend inductor --disable-cudagraphs --device cuda --only tacotron2
```
ctrl+c gives this stack information, whi…
-
### Describe the bug
I tried to train a French Tacotron2 model. Given the samples taken from training, it went perfectly well.
However, when inferring after training using sb's usual pipeline, the m…
-
Hi, thank you very much for the great work!
Could you please release the training codes to convert discrete ids to mel-spectrograms?
I was wondering how to train this tacotron2 model. The ground…
-
Hi, Thanks to this repository. I have a trained Text2Speech model(with custom data) on tacotron2 but when I try to convert my pytorch model to onnx, the outputted audio results are not as good as the …
-
I tried to convert the Tacotron2 Model to ONNX with your code.
But I got an error about the LSTM layer in the Encoder.
![Screenshot from 2021-04-02 17-25-58](https://user-images.githubusercontent.co…