https://github.com/thedhruvrawat/y-dat
Video transcription service built as a part of Practice School - I course at William O'Neil, Bangalore
https://github.com/thedhruvrawat/y-dat
google-speech-api speech-recognition youtube-transcript youtube-video-downloader
Last synced: 2 months ago
JSON representation
Video transcription service built as a part of Practice School - I course at William O'Neil, Bangalore
- Host: GitHub
- URL: https://github.com/thedhruvrawat/y-dat
- Owner: thedhruvrawat
- License: mit
- Created: 2021-07-06T12:10:56.000Z (almost 4 years ago)
- Default Branch: master
- Last Pushed: 2022-07-18T17:58:49.000Z (almost 3 years ago)
- Last Synced: 2025-01-03T19:46:33.124Z (4 months ago)
- Topics: google-speech-api, speech-recognition, youtube-transcript, youtube-video-downloader
- Language: Python
- Homepage:
- Size: 6.84 KB
- Stars: 1
- Watchers: 2
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Y-DAT: Youtube Video Download and Transcription
Allows the user to download Youtube video using it's URL (using `youtube_dl` library) and then generate it's transcript using `SpeechRecognizer` library
### Installation
Make sure you have `Python 3.5 or higher` installed along with `pip`.
#### Cloning the repository
```bash
git clone https://github.com/thedhruvrawat/y-dat.git
```
#### Installing the requirements
To install the requirements, run
```bash
pip install -r requirements.txt
```
### Downloading the video
To download the video from a link, run
```bash
python downloader.py -url
```
### Generating the transcript
To recognize the speech in video, run
```bash
python3 recognizer.py -video
```
By default, the video will be saved by the name `video.mkv`
The generated text will be saved in the file `transcript.txt`, along with this an `audio.wav` file containing solely the audio of the downloaded video will also be generated in the same folder. Works only for English language.
> Best results obtained when the audio is free from any kind of background sounds
### Further Reading
* [Youtube-dl](https://github.com/ytdl-org/youtube-dl)
* [SpeechRecognizer](https://github.com/Uberi/speech_recognition)
* [Librosa](https://github.com/librosa/librosa)
* [Russian-Subtitles-Generator](https://github.com/nestyme/Subtitles-generator)
### License
MIT