Example Use (from within model directory):

tts --text "this is Text for Tee tee ess" --out_path speech.wav --model_path checkpoint_85000.pth --config_path config.json --speakers_file_path vctk_speakers.json --speaker_idx VCTK_p277 --language_idx en

VCTK_p225: 23 year old female, English accent (Southern England)

VCTK_p228: 22 year old female, English accent (Southern England)

VCTK_p229: 23 year old female, English accent (Southern England)

VCTK_p230: 22 year old female, English accent (Stockton-on-tees)

VCTK_p231: 23 year old female, English accent (Southern England)

VCTK_p233: 23 year old female, English accent (Staffordshire)

VCTK_p236: 23 year old female, English accent (Manchester)

VCTK_p239: 22 year old female, English accent (Southwest England)

VCTK_p240: 21 year old female, English accent (Southern England)

VCTK_p244: 22 year old female, English accent (Manchester)

VCTK_p250: 22 year old female, English accent (Southeast England)

VCTK_p257: 24 year old female, English accent (Southern England)

VCTK_p267: 23 year old female, English accent (Yorkshire)

VCTK_p268: 23 year old female, English accent (Southern England)

VCTK_p269: 20 year old female, English accent (Newcastle)

VCTK_p276: 24 year old female, English accent (Oxford)

VCTK_p277: 23 year old female, English accent (Northeast England)

VCTK_p282: 23 year old female, English accent (Newcastle)

Built with YourTTS

Dataset: https://datashare.ed.ac.uk/handle/10283/2950

Downloads last month
29
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train voices/VCTK_British_English_Females