google colab

[willsionggg]

it was working fine but after this update not anymore

/content/tortoise-tts-fast/tortoise/models/vocoder.py:10 in │ │ │ │ 7 from typing import Optional, Callable │ │ 8 from dataclasses import dataclass │ │ 9 try: │ │ ❱ 10 │ from BigVGAN.models import BigVGAN as BVGModel │ │ 11 │ from BigVGAN.env import AttrDict │ │ 12 except ImportError: │ │ 13 │ raise ImportError( │ │ │ │ /content/BigVGAN/models.py:14 in │ │ │ │ 11 from torch.nn import Conv1d, ConvTranspose1d, Conv2d │ │ 12 from torch.nn.utils import weight_norm, remove_weight_norm, spectral_norm │ │ 13 │ │ ❱ 14 import activations │ │ 15 from utils import init_weights, get_padding │ │ 16 from alias_free_torch import * │ │ 17 │ ╰──────────────────────────────────────────────────────────────────────────────────────────────────╯ ModuleNotFoundError: No module named 'activations'

During handling of the above exception, another exception occurred:

╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮ │ /usr/local/lib/python3.9/dist-packages/IPython/core/interactiveshell.py:3326 in runcode │ │ │ │ 3323 │ │ │ │ elif async : │ │ 3324 │ │ │ │ │ await eval(code_obj, self.user_global_ns, self.user_ns) │ │ 3325 │ │ │ │ else: │ │ ❱ 3326 │ │ │ │ │ exec(code_obj, self.user_global_ns, self.user_ns) │ │ 3327 │ │ │ finally: │ │ 3328 │ │ │ │ # Reset our crash handler in place │ │ 3329 │ │ │ │ sys.excepthook = old_excepthook │ │ in │ │ │ │ /content/tortoise-tts-fast/tortoise/api.py:19 in │ │ │ │ 16 from tortoise.models.cvvp import CVVP │ │ 17 from tortoise.models.diffusion_decoder import DiffusionTts │ │ 18 from tortoise.models.random_latent_generator import RandomLatentConverter │ │ ❱ 19 from tortoise.models.vocoder import VocConf │ │ 20 from tortoise.utils.audio import denormalize_tacotron_mel, wav_to_univnet_mel │ │ 21 from tortoise.utils.diffusion import ( │ │ 22 │ SpacedDiffusion, │ │ │ │ /content/tortoise-tts-fast/tortoise/models/vocoder.py:13 in │ │ │ │ 10 │ from BigVGAN.models import BigVGAN as BVGModel │ │ 11 │ from BigVGAN.env import AttrDict │ │ 12 except ImportError: │ │ ❱ 13 │ raise ImportError( │ │ 14 │ │ "BigVGAN not installed, can't use BigVGAN vocoder\n" │ │ 15 │ │ "Please see the installation instructions on README." │ │ 16 │ ) │ ╰──────────────────────────────────────────────────────────────────────────────────────────────────╯ ImportError: BigVGAN not installed, can't use BigVGAN vocoder Please see the installation instructions on README.

[tanfarou]

Same issue on Windows local install.

[absane]

Solution:

cd BigVGAN
pip install -e .
cd ..

[willsionggg]

thank you it works and one thing you will need to download BigVGAN from here https://github.com/152334H/BigVGAN/tree/61dc4d24650d0900e00705af4c3473e07112a989 as this repo contain empty file of BigVGAN don't know why
anyway thank you for help

[absane]

as this repo contain empty file of BigVGAN don't know why

That's because git clone [url] doesn't pull sub-modules by default. I believe you can do it with this command:

git pull --recurse-submodules [url]

[152334H]

TIL about the differences between editable pip installations and normal package installations.

I have killed the submodule and correspondingly converted the BigVGAN fork to a real package. This should enable a fresh installation to work without error.