1# videocr
  2
  3Extract hardcoded subtitles from videos using the [Tesseract](https://github.com/tesseract-ocr/tesseract) OCR engine with Python.
  4
  5Input a video with hardcoded subtitles:
  6
  7<p float="left">
  8  <img width="430" alt="screenshot" src="https://user-images.githubusercontent.com/10210967/56873658-3b76dd00-6a34-11e9-95c6-cd6edc721f58.png">
  9  <img width="430" alt="screenshot" src="https://user-images.githubusercontent.com/10210967/56873659-3b76dd00-6a34-11e9-97aa-2c3e96fe3a97.png">
 10</p>
 11
 12```python
 13import videocr
 14
 15print(videocr.get_subtitles('video.avi', lang='chi_sim+eng', sim_threshold=70))
 16```
 17
 18Output:
 19
 20``` 
 210
 2200:00:01,042 --> 00:00:02,877
 23喝 点 什么 ? 
 24What can I get you?
 25
 261
 2700:00:03,044 --> 00:00:05,463
 28我 不 知道
 29Um, I'm not sure.
 30
 312
 3200:00:08,091 --> 00:00:10,635
 33休闲 时 光 …
 34For relaxing times, make it...
 35
 363
 3700:00:10,677 --> 00:00:12,595
 38三 得 利 时 光
 39Bartender, Bob Suntory time.
 40
 414
 4200:00:14,472 --> 00:00:17,142
 43我 要 一 杯 伏特 加
 44Un, I'll have a vodka tonic.
 45
 465
 4700:00:18,059 --> 00:00:19,019
 48谢谢
 49Laughs Thanks.
 50
 51```
 52
 53## Performance
 54
 55The OCR process runs in parallel and is CPU intensive. It takes 3 minutes on my dual-core laptop to extract a 20 seconds video. You may want more cores for longer videos.
 56
 57## API
 58
 59```python
 60videocr.get_subtitles(
 61        video_path: str, lang='eng', time_start='0:00', time_end='',
 62        conf_threshold=65, sim_threshold=90, use_fullframe=False)
 63```
 64Return the subtitles string in SRT format.
 65
 66
 67```python
 68
 69videocr.save_subtitles_to_file(
 70        video_path: str, file_path='subtitle.srt', lang='eng', time_start='0:00',
 71        time_end='', conf_threshold=65, sim_threshold=90, use_fullframe=False)
 72```
 73Write subtitles to `file_path`. If the file does not exist, it will be created automatically.
 74
 75### Parameters
 76
 77- `lang`
 78
 79  The language of the subtitles in the video. All language codes on [this page](https://github.com/tesseract-ocr/tesseract/wiki/Data-Files#data-files-for-version-400-november-29-2016) (e.g. `'eng'` for English) and all script names in [this repository](https://github.com/tesseract-ocr/tessdata_fast/tree/master/script) (e.g. `'HanS'` for simplified Chinese) are supported.
 80  
 81  Note that you can use more than one language. For example, `'hin+eng'` means using Hindi and English together for recognition. More details are available in the [Tesseract documentation](https://github.com/tesseract-ocr/tesseract/wiki/Command-Line-Usage#using-multiple-languages).
 82  
 83  Language data files will be automatically downloaded to your `$HOME/tessdata` directory when necessary. You can read more about Tesseract language data files on their [wiki page](https://github.com/tesseract-ocr/tesseract/wiki/Data-Files).
 84
 85- `time_start` and `time_end`
 86
 87  Extract subtitles from only a part of the video. The subtitle timestamps are still calculated according to the full video length.
 88
 89- `conf_threshold`
 90
 91  Confidence threshold for word predictions. Words with lower confidence than this threshold are discarded. The default value is fine for most cases. 
 92
 93  Make it closer to 0 if you get too few words from the predictions, or make it closer to 100 if you get too many excess words.
 94
 95- `sim_threshold`
 96
 97  Similarity threshold for subtitle lines. Neighbouring subtitles with larger [Levenshtein](https://en.wikipedia.org/wiki/Levenshtein_distance) ratios than this threshold will be merged together. The default value is fine for most cases.
 98
 99  Make it closer to 0 if you get too many duplicated subtitle lines, or make it closer to 100  if you get too few subtitle lines.
100
101- `use_fullframe`
102
103  By default, only the bottom half of each frame is used for OCR. You can explicitly use the full frame if your subtitles are not within the bottom half of each frame.
104