G-force78
commented
1 year ago Create folder in voices, add wav files to folder, select voice in arguments
!python tortoise/do_tts.py --text "This seems to work way better than on my local machine. The periods don't mess it up. Or do they?" --voice NEW VOICE --preset high_quality --candidates 1 --output_path results/random1
ValueError: voice clinton not available, use --list-voices to see available voices.
How can I add a voice (in a similar way that Tortoise does)?
python3 scripts/tortoise_tts.py --list-voices usage: tortoise_tts.py [-h] [-v str] [-V [str]] [-p {ultra_fast,fast,standard,high_quality}] [-q bool] [--voicefixer bool] [-l bool] [-P bool] [-o [Path]] [-O Path] [--candidates int] [--regenerate [str]] [--skip_existing bool] [--produce_debug_state bool] [--seed [int]] [--models_dir str] [--text_split [str]] [--disable_redaction bool] [--device [str]] [--batch_size [int]] [--vocoder {Univnet,BigVGAN,BigVGAN_Base}] [--ar_checkpoint [str]] [--clvp_checkpoint [str]] [--diff_checkpoint [str]] [--num_autoregressive_samples [int]] [--temperature [float]] [--length_penalty [float]] [--repetition_penalty [float]] [--top_p [float]] [--max_mel_tokens [int]] [--cvvp_amount [float]] [--diffusion_iterations [int]] [--cond_free [bool]] [--cond_free_k [float]] [--diffusion_temperature [float]] [--low_vram bool] [--half bool] [--no_cache bool] [--sampler {dpm++2m,p,ddim}] [--original_tortoise bool] text tortoise_tts.py: error: unrecognized arguments: --list-voices