https://github.com/snakers4/russian_stt_text_normalization

Russian text normalization pipeline for speech-to-text and other applications based on tagging s2s networks
https://github.com/snakers4/russian_stt_text_normalization

python3 pytorch russian-language speech speech-to-text text-normalization torchscript

Last synced: 3 months ago
JSON representation

Russian text normalization pipeline for speech-to-text and other applications based on tagging s2s networks

• Host: GitHub
• URL: https://github.com/snakers4/russian_stt_text_normalization
• Owner: snakers4
• License: gpl-3.0
• Archived: true
• Created: 2020-02-26T09:41:13.000Z (almost 5 years ago)
• Default Branch: master
• Last Pushed: 2021-03-15T06:25:03.000Z (almost 4 years ago)
• Last Synced: 2024-08-08T23:21:11.476Z (7 months ago)
• Topics: python3, pytorch, russian-language, speech, speech-to-text, text-normalization, torchscript
• Language: Python
• Homepage:
• Size: 3.03 MB
• Stars: 116
• Watchers: 7
• Forks: 15
• Open Issues: 5
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
![Normalization](https://pics.spark-in.me/upload/7c12fea58ff515ffb46df52b6050ace0.jpg)

# Russian STT Text Normalization

Russian text normalization pipeline for speech-to-text and other applications based on tagging s2s networks.

## Requirements

- Python >= 3.6

- [PyTorch](https://pytorch.org/get-started/locally/) >= 1.4 for s2s pipeline

- [tqdm](https://github.com/tqdm/tqdm) for progress bar

```

pip install torch

pip install tqdm

```

## Usage

```python

from normalizer import Normalizer

text = 'С 12.01.1943 г. площадь сельсовета — 1785,5 га.'

norm = Normalizer()

result = norm.norm_text(text)

print(result)

```

```

>>> С двенадцатого января тысяча девятьсот сорок третьего года площадь сельсовета

>>> — тысяча семьсот восемьдесят пять целых и пять десятых гектара

```