VitsAudioConfig cannot be imported

[artificialnouveau]

Hi there,

I'm trying to train a Vits model, I have tried to import the Vits model in google colab in two ways:

First approach:
! pip install TTS==0.7.1
import os

from trainer import Trainer, TrainerArgs

from TTS.tts.configs.shared_configs import BaseDatasetConfig
from TTS.tts.configs.vits_config import VitsConfig
from TTS.tts.datasets import load_tts_samples
from TTS.tts.models.vits import Vits, VitsAudioConfig
from TTS.tts.utils.text.tokenizer import TTSTokenizer
from TTS.utils.audio import AudioProcessor

I get the following error:
ImportError: cannot import name 'VitsAudioConfig' from 'TTS.tts.models.vits' (/usr/local/lib/python3.7/dist-packages/TTS/tts/models/vits.py)

Second approach:

! git clone https://github.com/coqui-ai/TTS
%cd TTS
! pip3 install -e
%cd

I get the following error:
ImportError: cannot import name 'VitsAudioConfig' from 'TTS.tts.models.vits' (/usr/local/lib/python3.7/dist-packages/TTS/tts/models/vits.py)

How can I import the VitsAudioConfig?

[p0p4k]

Because VitsAudioConfig is not implemented in v0.7.1.
Please download the dev branch.

! git clone -b dev https://github.com/coqui-ai/TTS
%cd TTS
! pip3 install -e
%cd

[artificialnouveau]

Thanks! I realize that now. It works. Best Regards, Ahnjili

…

On Aug 9, 2022, at 12:53, p0p4k ***@***.***> wrote:  Because VitsAudioConfig is not implemented in v0.7.1. Please download the dev branch. — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.