Wrong Windows installations guide in README

[arturstopa]

This part of readme is wrong.

Line

conda install pytorch torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia

doesn't work anymore. According to PyTorch docs for installation of older versions the correct line is

conda install pytorch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2 pytorch-cuda=11.7 -c pytorch -c nvidia

[Chovanec]

Also python setup.py install stops with error:
ModuleNotFoundError: No module named 'setuptools_rust'

[anmolbyte]

does anyone know how to fix the setuptools_rust error?

[arturstopa]

Remove the constraint on tokenizers package.

Also, python setup.py install is deprecated and raises a Warning, use pip install . instead.

[IamQisir]

Thank you! This is very helpful！

[lukaLLM]

So I followed it on win 11 and wanted to run it in python and use the example.ipynb but https://github.com/neonbjb/tortoise-tts/blob/main/tortoise_tts.ipynb but I got tortoise.api missing so I installed it using pip and now I have this. Or is there different example how to use it ?

import torch
import torchaudio
import torch.nn as nn
import torch.nn.functional as F
from tortoise.api import TextToSpeech
from tortoise.utils.audio import load_audio, load_voice, load_voices
# This will download all the models used by Tortoise from the HF hub.
tts = TextToSpeech()
# If you want to use deepspeed the pass use_deepspeed=True nearly 2x faster than normal
tts = TextToSpeech(use_deepspeed=True, kv_cache=True)
text = "Joining two modalities results in a surprising increase in generalization! What would happen if we combined them all?"

# Here's something for the poetically inclined.. (set text=)
"""
Then took the other, as just as fair,
And having perhaps the better claim,
Because it was grassy and wanted wear;
Though as for that the passing there
Had worn them really about the same,"""

# Pick a "preset mode" to determine quality. Options: {"ultra_fast", "fast" (default), "standard", "high_quality"}. See docs in api.py
preset = "ultra_fast"
# Pick one of the voices from the output above
voice = 'tom'

# Load it and send it through Tortoise.
voice_samples, conditioning_latents = load_voice(voice)
gen = tts.tts_with_preset(text, voice_samples=voice_samples, conditioning_latents=conditioning_latents, 
                          preset=preset)
torchaudio.save('generated.wav', gen.squeeze(0).cpu(), 24000)

ImportError: cannot import name 'chunk' from 'tortoise.utils' (\anaconda3\envs\tortoise2\lib\site-packages\tortoise\utils_init_.py)