-
**Describe the bug**
when trying to train the ljspeech recepie in my model I get the following error:
```
ohola@Aquarius:~/espnet/egs2/femaleryanspeech/tts1$ ./run.sh --stage 1 --stop-stage 1
20…
-
initializing preprocessing..
Selecting data folders..
Traceback (most recent call last):
File "preprocess.py", line 110, in
main()
File "preprocess.py", line 106, in main
run_prepro…
-
I can't run the demo server because of the checkpoint file cannot be found anyway! I'm working on Windows through Anaconda (because there were more problems to launch tacotron through regular Python).…
-
### Describe the bug
Hi,
I am trying to run the Tortoise model in tts-server but get an error.
I installed coqui environment on windows 10. I tried using venv and conda (separate installations) …
-
Hi:
I downloaded Mozilla TTS from Github, following the same steps you suggest in it. I am using my own dataset in the ljspeech format. I installed TTS but when I execute:
python TTS/bin/train_ta…
-
Currently, 40 models are passing `torchbench.py -d cuda --inductor --training --float16` mode, this issue tracks the ones that don't work. Note that due to `dropout()` RNG differences we don't expect …
-
I have been working with your code and have trained a diffusion decoder. I am now interested in evaluating the performance of the trained model. Specifically, I would like to use the trained decoder f…
-
Hello! I'm just starting to learn about text-to-speech, and found your project very instructive.
If I follow correctly, the MFA transcribed phonemes are later used for model training. I'm wondering…
-
Hello @imdanboy,
When i try to load the pretrained model from HuggingFace, it seems that `tts.discriminator.msd.discriminators.0.layers` should have `weight_v` and `weight_g` but it only has `weigh…
-
### Describe the bug
On an Apple Silicon M1 with MacOS Ventura, I could replicate the following for
- miniforge3
- mambaforge
and several models and vocoders.
### After the installation proc…