Error while training about persian-tts-coqui HOT 5 CLOSED

It was in fact because of the package version! Thank you for the help. I had another question regarding phonemizing the dataset, how did you phonemize your dataset? any specific tools? Thank you

from persian-tts-coqui.

Hi ,
1- could you please tell more info about your environment .Please send result of this code:

wget https://raw.githubusercontent.com/coqui-ai/TTS/main/TTS/bin/collect_env_info.py
python collect_env_info.py

2- Do you using jupyter notebook to run codes?If yes please save your notebook with all outputs and send it here.

from persian-tts-coqui.

Hello! I can tell you about the environment of course, but that python script "collect_env_info.py" does not run. I am running this on a docker container, which is running on a Linux server with multiple GPUs linked to the container. Thanks!

from persian-tts-coqui.

OK. please send full execution log.
Probably it is because of your installed packages version, I dont know too much about docker but these resources could help you :

• https://tts.readthedocs.io/en/latest/docker_images.html
• https://github.com/synesthesiam/coqui-docker

from persian-tts-coqui.

No , I just used espeak as phonemizer as you can see in my config use_phonemes=True, uses eSpeak as default phonemizer .You can change phonemizer ,

• https://tts.readthedocs.io/en/latest/models/vits.html?highlight=phonemizer#vitsconfig
• https://tts.readthedocs.io/en/latest/implementing_a_new_language_frontend.html?highlight=phonemizer#implementing-a-new-language-frontend

But there are some good libs for that , like persian_phonemizer
and also mimic-3 has a method that also solves kasre ezafe (Ezāfe) problem , here is the code for that _fix_words

from persian-tts-coqui.