public-mirrors/audiblez
1
0
Fork 0
mirror of https://github.com/santinic/audiblez.git synced 2025-09-18 21:40:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix espeak-ng

Browse source
This commit is contained in:
Claudio Santini 2025-01-30 16:04:58 +01:00
parent bf09d6ad82
commit acea1ac31c
3 changed files with 13 additions and 15 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
README.md
View file

@ -12,9 +12,9 @@ using Kokoro's high-quality speech synthesis.
[Kokoro-82M](https://huggingface.co/hexgrad/Kokoro-82M) is a recently published text-to-speech model with just 82M params and very natural sounding output.
It's released under Apache licence and it was trained on < 100 hours of audio.
It currently supports American and British English in a bunch of very good voices.
It currently supports American and British English in a bunch of very good voices.
**Future support for French, Korean, Japanese and Mandarin is planned.**
Future support for French, Korean, Japanese and Mandarin is planned.
On a Google Colab's T4 GPU via Cuda, **it takes about 5 minutes to convert "Animal's Farm" by Orwell** (which is a bout 160,000 characters) to audiobook, at a rate of about 600 characters per second.
@ -23,9 +23,12 @@ On my M2 MacBook Pro, on CPU, it takes about 1 hour, at a rate of about 60 chara
## How to install and run
If you have Python 3 on your computer, you can install it with pip.
You also need `espeak-ng` installed on your machine:
```bash
pip install audiblez
sudo apt install espeak-ng # on Ubuntu/Debian
brew install espeak-ng # on Mac
```
Then, to convert an epub file into an audiobook, just run:

6
audiblez.py
View file

@ -38,14 +38,14 @@ def main(pipeline, file_path, voice, pick_manually, speed):
meta_title = book.get_metadata('DC', 'title')
title = meta_title[0][0] if meta_title else ''
meta_creator = book.get_metadata('DC', 'creator')
creator = meta_creator[0][0] if meta_creator else ''
by_creator = 'by ' + meta_creator[0][0] if meta_creator else ''
cover_maybe = [c for c in book.get_items() if c.get_type() == ebooklib.ITEM_COVER]
cover_image = cover_maybe[0].get_content() if cover_maybe else b""
if cover_maybe:
print(f'Found cover image {cover_maybe[0].file_name} in {cover_maybe[0].media_type} format')
intro = f'{title} by {creator}'
intro = f'{title} {by_creator}'
print(intro)
print('Found Chapters:', [c.get_name() for c in book.get_items() if c.get_type() == ebooklib.ITEM_DOCUMENT])
if pick_manually:
@ -95,7 +95,7 @@ def main(pipeline, file_path, voice, pick_manually, speed):
print('Progress:', f'{progress}%\n')
if has_ffmpeg:
create_index_file(title, creator, chapter_mp3_files)
create_index_file(title, by_creator, chapter_mp3_files)
create_m4b(chapter_mp3_files, filename, cover_image)

15
test/test_main.py
View file

@ -1,3 +1,4 @@
import os
import unittest
from pathlib import Path
@ -11,11 +12,6 @@ class MainTest(unittest.TestCase):
pipeline = KPipeline(lang_code='a')
main(pipeline, file_path=file_path, voice='af_sky', pick_manually=False, speed=1, **kwargs)
# def test_0_txt(self):
# Path('book.m4b').unlink(missing_ok=True)
# self.base(file_path='../txt/book.txt')
# self.assertTrue(Path('book.m4b').exists())
def test_1_mini(self):
Path('mini.m4b').unlink(missing_ok=True)
self.base(file_path='../epub/mini.epub')
@ -26,12 +22,11 @@ class MainTest(unittest.TestCase):
self.base(file_path='../epub/poe.epub')
self.assertTrue(Path('poe.m4b').exists())
# def test_3_gene(self):
# Path('gene.m4b').unlink(missing_ok=True)
# self.base(file_path='../epub/gene.epub')
# self.assertTrue(Path('gene.m4b').exists())
def test_orwell(self):
Path('orwell.m4b').unlink(missing_ok=True)
os.system('rm orwell_chapter_*.wav')
self.base(file_path='../epub/orwell.epub')
self.assertTrue(Path('orwell.m4b').exists())
for i in range(8):
self.assertTrue(Path(f'orwell_chapter_{i}.wav').exists())
self.assertTrue(Path(f'orwell_chapter_{i}.wav').stat().st_size > 300 * 1024, 'file should be larger than 300KB, surely failed')