Spaces:

coqui

/

xtts

like 1.52k

Running on T4

Hi, the code had a bug that raised a error in CPU run. It was fixed here https://github.com/coqui-ai/TTS/pull/2951.

To be able to run it on CPU you need to install Coqui TTS from the dev branch:
python3 -m pip install https://github.com/coqui-ai/TTS

And then follow the docs here setting gpu = False

from TTS.api import TTS
tts = TTS("tts_models/multilingual/multi-dataset/xtts_v1", gpu=False)

# generate speech by cloning a voice using default settings
tts.tts_to_file(text="It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.",
                file_path="output.wav",
                speaker_wav="/path/to/target/speaker.wav",
                language="en")

# generate speech by cloning a voice using custom settings
tts.tts_to_file(text="It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.",
                file_path="output.wav",
                speaker_wav="/path/to/target/speaker.wav",
                language="en",
                decoder_iterations=30)

Best regardings,
Edresson Casanova

please check this space for example

https://huggingface.co/spaces/Olivier-Truong/XTTS_V1_CPU_working

THX you all