Can't seem to find the dirty bastard

[Glazkor]

Where the hell is the voices/ directory?

[I-Have-No-Idea-What-IAmDoing]

tortoise-tts\tortoise\voices

[Glazkor]

?

[Glazkor]

nvm, had a problem with the git install on miniconda

[neonbjb]

Just want to mention that this is the best discussion title I've yet seen.

[Glazkor]

thank you, but look what is happening
Traceback (most recent call last):
File "tortoise/do_tts.py", line 4, in
import torch
File "C:\Users\Aionecleis\miniconda3\envs\tortoise-tts\lib\site-packages\torch_init_.py", line 189, in
from torch._C import *
ImportError: numpy.core.multiarray failed to import

[neonbjb]

Some sort of pytorch installation problem. Try looking over at the pytorch forums for this error message.

[Glazkor]

(base) C:\Users\Aionecleis\tortoise-tts>python tortoise/do_tts.py --text "I'm going to speak this" --voice ancestor --preset fast
C:\Users\Aionecleis\miniconda3\lib\site-packages\torchaudio_internal\module_utils.py:99: UserWarning: Failed to import soundfile. 'soundfile' backend is not available.
warnings.warn("Failed to import soundfile. 'soundfile' backend is not available.")
Traceback (most recent call last):
File "C:\Users\Aionecleis\miniconda3\lib\site-packages\soundfile.py", line 143, in
_snd = _ffi.dlopen(_libname)
OSError: cannot load library 'C:\Users\Aionecleis\miniconda3\Library\bin\sndfile.dll': error 0x7e

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "C:\Users\Aionecleis\tortoise-tts\tortoise\do_tts.py", line 7, in
from api import TextToSpeech, MODELS_DIR
File "C:\Users\Aionecleis\tortoise-tts\tortoise\api.py", line 22, in
from tortoise.utils.audio import wav_to_univnet_mel, denormalize_tacotron_mel
File "C:\Users\Aionecleis\miniconda3\lib\site-packages\tortoise-2.4.2-py3.9.egg\tortoise\utils\audio.py", line 4, in
import librosa
File "C:\Users\Aionecleis\miniconda3\lib\site-packages\librosa_init_.py", line 209, in
from . import core
File "C:\Users\Aionecleis\miniconda3\lib\site-packages\librosa\core_init_.py", line 6, in
from .audio import * # pylint: disable=wildcard-import
File "C:\Users\Aionecleis\miniconda3\lib\site-packages\librosa\core\audio.py", line 8, in
import soundfile as sf
File "C:\Users\Aionecleis\miniconda3\lib\site-packages\soundfile.py", line 162, in
_snd = _ffi.dlopen(_os.path.join(
OSError: cannot load library 'C:\Users\Aionecleis\miniconda3\lib\site-packages_soundfile_data\libsndfile64bit.dll': error 0x7e

(base) C:\Users\Aionecleis\tortoise-tts>pip install soundfile
Requirement already satisfied: soundfile in c:\users\aionecleis\miniconda3\lib\site-packages (0.10.3.post1)
Requirement already satisfied: cffi>=1.0 in c:\users\aionecleis\miniconda3\lib\site-packages (from soundfile) (1.15.0)
Requirement already satisfied: pycparser in c:\users\aionecleis\miniconda3\lib\site-packages (from cffi>=1.0->soundfile) (2.21)

(base) C:\Users\Aionecleis\tortoise-tts>python tortoise/do_tts.py --text "I'm going to speak this" --voice random --preset fast
C:\Users\Aionecleis\miniconda3\lib\site-packages\torchaudio_internal\module_utils.py:99: UserWarning: Failed to import soundfile. 'soundfile' backend is not available.
warnings.warn("Failed to import soundfile. 'soundfile' backend is not available.")
Traceback (most recent call last):
File "C:\Users\Aionecleis\miniconda3\lib\site-packages\soundfile.py", line 143, in
_snd = _ffi.dlopen(_libname)
OSError: cannot load library 'C:\Users\Aionecleis\miniconda3\Library\bin\sndfile.dll': error 0x7e

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "C:\Users\Aionecleis\tortoise-tts\tortoise\do_tts.py", line 7, in
from api import TextToSpeech, MODELS_DIR
File "C:\Users\Aionecleis\tortoise-tts\tortoise\api.py", line 22, in
from tortoise.utils.audio import wav_to_univnet_mel, denormalize_tacotron_mel
File "C:\Users\Aionecleis\miniconda3\lib\site-packages\tortoise-2.4.2-py3.9.egg\tortoise\utils\audio.py", line 4, in
import librosa
File "C:\Users\Aionecleis\miniconda3\lib\site-packages\librosa_init_.py", line 209, in
from . import core
File "C:\Users\Aionecleis\miniconda3\lib\site-packages\librosa\core_init_.py", line 6, in
from .audio import * # pylint: disable=wildcard-import
File "C:\Users\Aionecleis\miniconda3\lib\site-packages\librosa\core\audio.py", line 8, in
import soundfile as sf
File "C:\Users\Aionecleis\miniconda3\lib\site-packages\soundfile.py", line 162, in
_snd = _ffi.dlopen(_os.path.join(
OSError: cannot load library 'C:\Users\Aionecleis\miniconda3\lib\site-packages_soundfile_data\libsndfile64bit.dll': error 0x7e

???

[neonbjb]

Some kind of soundfile issue. The error is telling you that the statement import librosa is failing, which is not a Tortoise issue. I recommend looking around the librosa forums. Sorry.