1# videocr
 2
 3Extract hardcoded subtitles from videos using the [Tesseract](https://github.com/tesseract-ocr/tesseract) OCR engine with Python.
 4
 5Input 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='HanS'))
16```
17
18Output:
19
20``` 
210
2200:00:00,000 --> 00:00:02,711
23-谢谢 … 你 好 -谢谢
24Thank you...Hi. Thanks.
25
261
2700:00:02,794 --> 00:00:04,879
28喝 点 什么 ?
29What can I get you?
30
312
3200:00:05,046  --> 00:00:12,554
33休闲 时 光 …
34For relaxing times, make it...
35
363
3700:00:12,804 --> 00:00:14,723
38三 得 利 时 光
39Bartender, Bob Suntory time.
40
414
4200:00:16,474 --> 00:00:19,144
43Un, I'll have a vodka tonic.
44
455
4600:00:19,394 --> 00:00:20,687
47谢谢
48Laughs Thanks.
49
50```
51
52## API
53
54```python
55videocr.get_subtitles(
56        video_path: str, lang='eng', time_start='0:00', time_end='',
57        conf_threshold=65, sim_threshold=90, use_fullframe=False)
58```
59Return the subtitles string in SRT format.
60
61
62```python
63
64videocr.save_subtitles_to_file(
65        video_path: str, file_path='subtitle.srt', lang='eng', time_start='0:00',
66        time_end='', conf_threshold=65, sim_threshold=90, use_fullframe=False)
67```
68Write subtitles to `file_path`. If the file does not exist, it will be created automatically.
69
70## Adjustable Parameters
71
72- `lang`
73
74  Language of the subtitles in the video. 
75
76- `time_start` and `time_end`
77
78  Extract subtitles from only a part of the video. The subtitle timestamps are still calculated according to the full video length.
79
80- `conf_threshold`
81
82  Confidence threshold for word predictions. Words with lower confidence than this threshold are discarded. The default value is fine for most cases. 
83
84  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.
85
86- `sim_threshold`
87
88  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.
89
90  Make it closer to 0 if you get too few subtitle lines, or make it closer to 100 if you get too many duplicated subtitles.
91
92- `use_fullframe`
93
94  By default, only the bottom half of each frame is used for OCR in order to reduce errors. You can explicitly make the algorithm handle the full frame.