Application won't start #44

mbassano · 2024-10-17T09:40:21Z

mbassano
Oct 17, 2024

I'm new to WSL and Ubuntu. I've followed the installation instructions for Windows 11 and did see a number of red error messages scroll by. After the installation was complete I tried to start the GUI, but I get the following error:

Starting...
Traceback (most recent call last):
File "/home/mbassano/VoxNovel/gui_run.py", line 31, in
import pandas as pd
ModuleNotFoundError: No module named 'pandas'

The headless (whatever that is) won't start either:

Starting...
Traceback (most recent call last):
File "/home/mbassano/VoxNovel/headless_voxnovel.py", line 58, in
import pandas as pd
ModuleNotFoundError: No module named 'pandas'

How can I fix this?

mbassano · 2024-10-17T13:16:19Z

mbassano
Oct 17, 2024
Author

OK, so I found the solution (pip install pandas) in the comments of the video. I can now start the application and select an ebook. But after a short while of processing it crashes with the following error:

Exception in Tkinter callback
Traceback (most recent call last):
File "/home/mbassano/miniconda/envs/VoxNovel/lib/python3.10/tkinter/init.py", line 1921, in call
return self.func(*args)
File "/home/mbassano/VoxNovel/gui_run.py", line 438, in process_file
booknlp = BookNLP("en", model_params)
File "/home/mbassano/miniconda/envs/VoxNovel/lib/python3.10/site-packages/booknlp/booknlp.py", line 14, in init
self.booknlp=EnglishBookNLP(model_params)
File "/home/mbassano/miniconda/envs/VoxNovel/lib/python3.10/site-packages/booknlp/english/english_booknlp.py", line 148, in init
self.entityTagger=LitBankEntityTagger(self.entityPath, tagsetPath)
File "/home/mbassano/miniconda/envs/VoxNovel/lib/python3.10/site-packages/booknlp/english/entity_tagger.py", line 21, in init
self.model.to(device)
File "/home/mbassano/miniconda/envs/VoxNovel/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1174, in to
return self._apply(convert)
File "/home/mbassano/miniconda/envs/VoxNovel/lib/python3.10/site-packages/torch/nn/modules/module.py", line 780, in _apply
module._apply(fn)
File "/home/mbassano/miniconda/envs/VoxNovel/lib/python3.10/site-packages/torch/nn/modules/module.py", line 805, in _apply
param_applied = fn(param)
File "/home/mbassano/miniconda/envs/VoxNovel/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1160, in convert
return t.to(
RuntimeError: CUDA error: the launch timed out and was terminated
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

Any help would be greatly appreciated.

0 replies

DrewThomasson · 2024-10-17T13:28:48Z

DrewThomasson
Oct 17, 2024
Maintainer

Idk probs not enough vram

0 replies

DrewThomasson · 2024-10-17T13:30:11Z

DrewThomasson
Oct 17, 2024
Maintainer

Try throwing this book at it idk

https://github.com/DrewThomasson/ebook2audiobookXTTS/blob/main/demo_mini_story_chapters_Drew.epub

It's a test ebook that should be able to run on the worse GPU

This'll tell us if you just don't have a good enough GPU

0 replies

mbassano · 2024-10-17T13:43:46Z

mbassano
Oct 17, 2024
Author

Thanks for the quick reply!
I don't think it's GPU related, since it crashes during conversion to TXT (also with your sample ebook):

1% Converting input to HTML...
InputFormatPlugin: EPUB Input running
on /home/mbassano/VoxNovel/eBooks/demo_mini_story_chapters_Drew.epub
Found HTML cover titlepage.xhtml
Parsing all content...
34% Running transforms on e-book...
Merging user specified metadata...
Detecting structure...
Detected chapter: Chapter 1: It Continues
Detected chapter: Chapter 2: The Silk Road Odyssey
Flattening CSS and remapping font sizes...
Source base font size is 12.00000pt
Removing fake margins...
Cleaning up manifest...
Trimming unused files from manifest...
Creating TXT Output...
67% Running TXT Output plugin
Converting XHTML to TXT...
TXT output written to /home/mbassano/VoxNovel/eBooks/demo_mini_story_chapters_Drew.txt
Output saved to /home/mbassano/VoxNovel/eBooks/demo_mini_story_chapters_Drew.txt
{'pipeline': 'entity,quote,supersense,event,coref', 'model': 'big'}
/home/mbassano/miniconda/envs/VoxNovel/lib/python3.10/site-packages/transformers/modeling_utils.py:463: FutureWarning: You are using torch.load with weights_only=False (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for weights_only will be flipped to True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
return torch.load(checkpoint_file, map_location="cpu")
Exception in Tkinter callback
Traceback (most recent call last):
File "/home/mbassano/miniconda/envs/VoxNovel/lib/python3.10/tkinter/init.py", line 1921, in call
return self.func(*args)
File "/home/mbassano/VoxNovel/gui_run.py", line 438, in process_file
booknlp = BookNLP("en", model_params)
File "/home/mbassano/miniconda/envs/VoxNovel/lib/python3.10/site-packages/booknlp/booknlp.py", line 14, in init
self.booknlp=EnglishBookNLP(model_params)
File "/home/mbassano/miniconda/envs/VoxNovel/lib/python3.10/site-packages/booknlp/english/english_booknlp.py", line 148, in init
self.entityTagger=LitBankEntityTagger(self.entityPath, tagsetPath)
File "/home/mbassano/miniconda/envs/VoxNovel/lib/python3.10/site-packages/booknlp/english/entity_tagger.py", line 21, in init
self.model.to(device)
File "/home/mbassano/miniconda/envs/VoxNovel/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1174, in to
return self._apply(convert)
File "/home/mbassano/miniconda/envs/VoxNovel/lib/python3.10/site-packages/torch/nn/modules/module.py", line 780, in _apply
module._apply(fn)
File "/home/mbassano/miniconda/envs/VoxNovel/lib/python3.10/site-packages/torch/nn/modules/module.py", line 805, in _apply
param_applied = fn(param)
File "/home/mbassano/miniconda/envs/VoxNovel/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1160, in convert
return t.to(
RuntimeError: CUDA error: the launch timed out and was terminated
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

1 reply

DrewThomasson Oct 17, 2024
Maintainer

Still seeing GPU related issues...

Idk I'll reinstall later on my computer and see if the install is broken

mbassano · 2024-10-17T13:49:59Z

mbassano
Oct 17, 2024
Author

BTW: here's a summary of my hardware specs:

Summary
Operating System
Windows 11 Pro 64-bit
CPU
Intel Core i7 8700 @ 3.20GHz 39 °C
Coffee Lake 14nm Technology
RAM
64,0GB Dual-Channel DDR4 @ 1063MHz (15-15-15-36)
Motherboard
ASUSTeK COMPUTER INC. WS C246M PRO Series (CPU1) 39 °C
Graphics
S24C450 (1920x1080@60Hz)
LG Ultra HD (3840x2160@60Hz)
2047MB NVIDIA GeForce GTX 950 (MSI) 57 °C
Storage
1863GB Hitachi HDS5C3020ALA632 (SATA ) 39 °C
11176GB TOSHIBA MG07ACA12TE (SATA ) 36 °C
476GB SK hynix BC711 HFM512GD3JX013N (Unknown (SSD))
Optical Drives
HL-DT-ST BD-RE BH08LS20
TSSTcorp CDDVDW SH-224DB
Audio
Realtek High Definition Audio

I think my PC should be up to the task... ;-)

21 replies

DrewThomasson Oct 17, 2024
Maintainer

Great I'll just point you to all of my repos depending on your use lol

Anyway main thing is in the meantime here's the current web-interface docker image implantations:

For normal audiobooks where there is only one speaker (recommended less buggy):

Ebook2audiobookxtts

Ebook2audiobookxtts-web-demo-plz run locally this is only to show you the gui it's super slow

To run locally in docker:

docker run -it -p 7860:7860 --platform=linux/amd64 registry.hf.space/drewthomasson-ebook2audiobookxtts:latest python app.py

It's based on my github repo:

Ebook2audiobookxtts

For multiple voices (Ie give each character a different voice IE:VoxNovel:

For a current version of auto-run VoxNovel where it selects your voices for you automatically after you give it the ebook:

English only ebooks btw for VoxNovel

Auto-VoxNovel-web-demo

docker run -it -p 7860:7860 --platform=linux/amd64 registry.hf.space/drewthomasson-auto-voxnovel-demo:latest python app.py

For version where you can still select the voices but it's a terminal-like only interface IE-headless

English only ebooks btw for VoxNovel

Headless-VoxNovel-web-demo

To run locally in docker:

docker run -it -p 7860:7860 --platform=linux/amd64 registry.hf.space/drewthomasson-headless-voxnovel-demo:latest python app.py

DrewThomasson Oct 17, 2024
Maintainer

Keep in mind also, you only have cpu so these will all run slowly as they use XTTS

So for a 5 hour audiobook will probs takes like 8 hours to generate on your computer,

But like the outputs are great lol as seen here

output example from

Ebook2audiobookxtts

Ebook2audiobookxtts demo

Cloning this voice:

https://youtu.be/DkgozEpaeLw?si=RfWhk7Vm-LvHq4Dt

Magic.Tree.House.45.Osborne.Mary.Pope.-.A.Crazy.Day.With.Cobras.mp4

mbassano Oct 17, 2024
Author

I does sound good, but 8 hours for a 5 hour audiobook...... :-( Well, I think I'll play around with it for a bit anyway. Thanks for the info!

DrewThomasson Oct 17, 2024
Maintainer

Yeah I know lol

You'll have to get a nvidia GPU with at least 4gb VRAM for 5 hours generation time for a 5 hour audiobook ;/

(You can probs find one used for like 50$ online lol)

For cpu only the best option is probs this lol

https://huggingface.co/spaces/drewThomasson/ebook2audiobookpiper-tts

https://github.com/DrewThomasson/ebook2audiobookpiper-tts

mbassano Oct 18, 2024
Author

Thanks for the links.
Well, 5 hours is still much, much longer than I thought it would take... I was hoping something like 1 hour top per novel..... ;-) I guess I was overly optimistic about the state of the technology. Well, maybe I'll check back in a couple of years... lol.

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Application won't start #44

{{title}}

Replies: 5 comments 22 replies

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{title}}

{{editor}}'s edit

{{editor}}'s edit

{{title}}

{{editor}}'s edit

{{editor}}'s edit

{{title}}

{{title}}

{{editor}}'s edit

{{editor}}'s edit

{{title}}

Select a reply

Application won't start #44

mbassano Oct 17, 2024

Replies: 5 comments · 22 replies

mbassano Oct 17, 2024 Author

DrewThomasson Oct 17, 2024 Maintainer

DrewThomasson Oct 17, 2024 Maintainer

mbassano Oct 17, 2024 Author

DrewThomasson Oct 17, 2024 Maintainer

mbassano Oct 17, 2024 Author

DrewThomasson Oct 17, 2024 Maintainer

For normal audiobooks where there is only one speaker (recommended less buggy):

Ebook2audiobookxtts

To run locally in docker:

It's based on my github repo:

For multiple voices (Ie give each character a different voice IE:VoxNovel:

For a current version of auto-run VoxNovel where it selects your voices for you automatically after you give it the ebook:

For version where you can still select the voices but it's a terminal-like only interface IE-headless

To run locally in docker:

DrewThomasson Oct 17, 2024 Maintainer

output example from

Ebook2audiobookxtts demo

mbassano Oct 17, 2024 Author

DrewThomasson Oct 17, 2024 Maintainer

mbassano Oct 18, 2024 Author

mbassano
Oct 17, 2024

Replies: 5 comments 22 replies

mbassano
Oct 17, 2024
Author

DrewThomasson
Oct 17, 2024
Maintainer

DrewThomasson
Oct 17, 2024
Maintainer

mbassano
Oct 17, 2024
Author

DrewThomasson Oct 17, 2024
Maintainer

mbassano
Oct 17, 2024
Author

DrewThomasson Oct 17, 2024
Maintainer

DrewThomasson Oct 17, 2024
Maintainer

mbassano Oct 17, 2024
Author

DrewThomasson Oct 17, 2024
Maintainer

mbassano Oct 18, 2024
Author