-
Hi
I am curious if we increase the number of layers for the duration, pitch, and energy using the 'duration_predictor_layers' parameter and some other parameters in the architecture, will it improve…
-
Hello!
I already trained a Tacotron 2 model on my custom dataset based on LJspeech recipe and would like to train FastSpeech 2 model. When I ran the following command-
> ./run.sh --stage 5 --tra…
-
Hi, I got to know about your work through this discussion thread in coquiTTS : https://github.com/coqui-ai/TTS/discussions/930 and found your dataset included in TTS/recipes as well. I am interested i…
-
hello, thanks for the project. It's amazing what is capable to do.
I've been using the server as descibed here:
Create a fresh virtual environment with Python 3.6
$ apt-get install espeak libsnd…
-
$ python tortoise/do_tts.py --text "I'm going to speak this" --voice random --preset fast
C:\Users\Gautam\AppData\Local\Programs\Python\Python310\lib\site-packages\torchaudio\_internal\module_utils.p…
-
### Describe the bug
Arch Linux (Kernel 5.17.9)
AMD Ryzen 5 5500U
20GB RAM
When using tts_models/en/ljspeech/tacotron2-DDC_ph with vocoder_models/en/ljspeech/univnet, the output breaks off mid-s…
-
Hi all
I am non-German speaker and I am trying to train a Tacotron 2 model on your dataset which by the way is a great job and contribution.
Any comments on how to do a character level tokenizatio…
-
**Describe the bug**
Attempting to train a tacotron model on Windows (Anaconda) fails immediately due to `multiprocessing` configured to use `fork`. [Multiprocessing#Contexts and start methods](https…
-
### Hi,
I want to add language ID embedding to my FastSpeech2 model.
The file says that i have to add this to my config file.
`tts_conf:
langs: 4 # Number of languages`
But I want to as…
-
**Describe the bug**
Tacotron 2 TTS model inference is not thread-safe despite being in eval mode and results in various runtime errors (shared below) due to shared decoder internal states being wr…