Update README.md
Browse files
README.md
CHANGED
|
@@ -3,31 +3,31 @@ license: mit
|
|
| 3 |
---
|
| 4 |
# Create dataset from video
|
| 5 |
|
| 6 |
-
|
| 7 |
|
| 8 |
-
|
| 9 |
|
| 10 |
-
*(
|
| 11 |
|
| 12 |
-
###
|
| 13 |
|
| 14 |
-
1.
|
| 15 |
-
2.
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
3.
|
| 19 |
-
|
| 20 |
-
|
| 21 |
|
| 22 |
-
4.
|
| 23 |
-
|
| 24 |
|
| 25 |
-
5.
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
6. Запустите скрипт. Все обработанные диалоги будут автоматически сохранены в чистый `.txt` файл.
|
| 30 |
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
*
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
# Create dataset from video
|
| 5 |
|
| 6 |
+
This project contains a script based on an OpenAI model that will help you automatically create your own text dataset from video files or podcasts.
|
| 7 |
|
| 8 |
+
Under the hood, it uses the powerful **Whisper-Large-V3** model, which can accept the following audio and video formats: .mp3, .m4a, .wav, .mp4, .mkv, and .webm.
|
| 9 |
|
| 10 |
+
*(We recommend using the .mp3 and .mp4 formats for best compatibility and performance.)*
|
| 11 |
|
| 12 |
+
### Installation and Run
|
| 13 |
|
| 14 |
+
1. Make sure you have Python 3.9 or later installed.
|
| 15 |
+
2. Install FFmpeg (required, as extracting audio from video won't work without it).
|
| 16 |
+
* On Windows, open a command prompt and enter:
|
| 17 |
+
`winget install ffmpeg`
|
| 18 |
+
3. Install PyTorch with support for your graphics card (CUDA) for faster recognition:
|
| 19 |
+
```bash
|
| 20 |
+
pip install torch torchvision torchaudio --index-url [https://download.pytorch.org/whl/cu121](https://download.pytorch.org/whl/cu121)
|
| 21 |
|
| 22 |
+
4. Install the necessary libraries for working with the model:
|
| 23 |
+
pip install transformers accelerate
|
| 24 |
|
| 25 |
+
5. Create two empty folders in the script folder:
|
| 26 |
+
* `Videos` (place your videos here)
|
| 27 |
+
* `model` (for local storage of Whisper weights).
|
|
|
|
|
|
|
| 28 |
|
| 29 |
+
6. Run the script. All processed dialogs will be automatically saved to a clean .txt file.
|
| 30 |
+
|
| 31 |
+
**⚠️ Licensing Information:**
|
| 32 |
+
* The code portion of this project (automation scripts) is distributed under the MIT license.
|
| 33 |
+
* The Whisper neural network model itself, developed by OpenAI, is distributed under the Apache 2.0 license.
|