53 lines
1.3 KiB
Markdown
53 lines
1.3 KiB
Markdown
# AI Video Transcriber & Translator
|
|
|
|
This tool extracts audio from videos, transcribes it using OpenAI's Whisper model, and translates the transcript using Google's Gemini API.
|
|
|
|
## Setup
|
|
|
|
1. **Install Dependencies:**
|
|
```bash
|
|
pip install -r requirements.txt
|
|
```
|
|
*Note: You need `ffmpeg` installed on your system.*
|
|
|
|
2. **API Key:**
|
|
Set your Gemini API key as an environment variable:
|
|
```bash
|
|
export GEMINI_API_KEY="your_api_key_here"
|
|
```
|
|
|
|
## Usage
|
|
|
|
### Linux / Mac
|
|
Run the wizard script:
|
|
```bash
|
|
./run_v2.py
|
|
```
|
|
|
|
### Windows
|
|
1. **Install FFmpeg:** Download from [ffmpeg.org](https://ffmpeg.org/download.html) and add the `bin` folder to your System PATH.
|
|
2. **Run:** Double-click `run_v2.bat`.
|
|
* It will automatically create the virtual environment, install dependencies, and launch the tool.
|
|
|
|
### Manual CLI
|
|
```bash
|
|
python ai_transcriber_v2/main.py <path_to_video> [options]
|
|
```
|
|
|
|
### Options:
|
|
* `--model`: Whisper model size (`tiny`, `base`, `small`, `medium`, `large`). Default: `base`.
|
|
* `--lang`: Target language for translation. Default: `English`.
|
|
* `--force`: Overwrite existing transcript/translation files.
|
|
|
|
### Examples:
|
|
|
|
**Single File:**
|
|
```bash
|
|
python main.py ../my_video.mp4
|
|
```
|
|
|
|
**Entire Directory (Recursive):**
|
|
```bash
|
|
python main.py ../videos_folder/ --lang "Spanish" --model small
|
|
```
|