-
```
[ root @VM-0- 15-centos MoeTTS]# python main.py -tt2ck . /models/atri v2 40000.pt -hgck . /models/g atri hi
figan_ 02510000.pt -hgc . /models/config. json -i私社高性能飞少. -0 output -P basic cleaners
…
-
Repro:
```
benchmarks/torchbench.py -d cuda --inductor --float32 --no-skip --training -k tacotron2
```
Error:
```
Traceback (most recent call last):
File "/fsx/users/binbao/torchdynamo-tip/be…
-
Running this step:
```
#@title Install pipeline
#!pip install -q torch==1.9.0 torchvision==0.10.0 torchaudio==0.9.0
!pip install -q git+https://github.com/uberduck-ai/uberduck-ml-dev.git
```
…
-
### Describe the bug
I got error when set characters in tacoron 2, here's my train.py
```
import os
from trainer import Trainer, TrainerArgs
from TTS.config.shared_configs import BaseAudi…
-
Is there any data on performance benchmark for various GPU memory / batch size configurations? I am using 15gb single GPU. Unless I use 16 for batch size, it throws OOM. With 16 batch size it take…
-
### 🐛 Describe the bug
I am trying to convert tacotron2 model trained using nemo code base to onnx. And I am getting this error -> RuntimeError: Dynamic shape axis should be no more than the shape …
-
Click to expand!
### Issue Type
Bug
### Have you reproduced the bug with TF nightly?
Yes
### Source
source
### Tensorflow Version
2.11.0
### Custom Code
Yes
### OS Platform and Distribut…
-
微博内容精选
-
Hi, I'm trying to train multi speaker gst-tacotron2 tts moduleusing vctk corpus
I've set my cd as follows:
cd espnet/egs2/vctk/tts1
and tried to run the training with command:
./run.sh --tr…
-
I try to solve the issue by setting cudnn.enabled=false, change the version of cuda, and I try to reduce the num of workers and batch_size. But the error still occurs. Have you encountered same proble…