ivan provalov

Glow TTS Avg Loss Not Decreasing - Spanish LJSpeech Dataset

14

### Describe the bug When I train Glow TTS on LJSpeech Spanish set (angelina or victor) from [AI Labs](https://www.caito.de/2019/01/03/the-m-ailabs-speech-dataset/), the avg loss stays constant. Victor (4k steps, large batch size,...

"RuntimeError: [!] NaN loss with loss" on GlowTTS introduction example - mailabs dataset

5

### Describe the bug After running the introduction example on a single speaker ljspeech, I switched to mailabs format where the speaker are derived from the folder structure. I am...

Address Already in Use Error When Training on 2 GPUS and Starting a New Job on the Remaining 2 GPUS

15

### Describe the bug Following the steps on the [tutorial] (https://tts.readthedocs.io/en/latest/tutorial_for_nervous_beginners.html) GlowTTS: `python3 -m trainer.distribute --script train.py --gpus "0,1"` Vocoder: `python3 -m trainer.distribute --script train_vocoder.py --gpus "2,3"` Getting this exception...

Performance Benchmark

1

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...

Vanilla javascript websocket with microphone example

2

Vanilla javascript websocket client using AudioWorklet

Java standalone client with Mic Example. Using websocket.

Is there a plan for adding a Ukrainian and Romanian models in XTTS?

SentenceTransformer Unrecognized option: -c

4

**Describe the bug** Getting this exception ``` Unrecognized option: -c Error: Could not create the Java Virtual Machine. Error: A fatal exception has occurred. Program will exit. ``` When calling...

AES Serialization, jdk 11.

Is there a CMakeLists.txt or any other tooling for compiling crfsuite for Android? Thank you!