https://github.com/notyusheng/transcribe-translate
Local web app for transcription and translation services for audio and video using Whisper models
https://github.com/notyusheng/transcribe-translate
docker full-stack nodejs react reactjs self-hosted speech-to-text transcribe translate whisper
Last synced: 6 months ago
JSON representation
Local web app for transcription and translation services for audio and video using Whisper models
- Host: GitHub
- URL: https://github.com/notyusheng/transcribe-translate
- Owner: NotYuSheng
- License: mit
- Created: 2024-08-28T06:36:14.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2024-12-22T03:03:44.000Z (over 1 year ago)
- Last Synced: 2025-01-31T21:11:29.890Z (over 1 year ago)
- Topics: docker, full-stack, nodejs, react, reactjs, self-hosted, speech-to-text, transcribe, translate, whisper
- Language: JavaScript
- Homepage: https://transcribe-translate-frontend.onrender.com/
- Size: 8.93 MB
- Stars: 1
- Watchers: 0
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- Contributing: .github/CONTRIBUTING.md
- License: LICENSE
- Code of conduct: .github/CODE_OF_CONDUCT.md
- Security: .github/SECURITY.md
Awesome Lists containing this project
README
# Transcribe-Translate
Full Page Sample
## Host requirements
- **Docker**: [[Installation Guide](https://docs.docker.com/engine/install/)]
- **Docker Compose**: [[Installation Guide](https://docs.docker.com/compose/install/)]
- Compatibile with Linux and Windows Host
- Ensure port 8000 is not already in use
- Project can be ran on either CPU or GPU
## Model requirements
The following table outlines the recommended hardware requirements for each Whisper model based on typical usage scenarios. Please ensure that your system meets or exceeds these specifications for optimal performance.
| Model | Size (GB) | Minimum RAM (GB) | Recommended RAM (GB) | GPU Memory (VRAM) (GB) | Notes |
|------------|:----------:|:----------------:|:--------------------:|:----------------------:|---------------------------------------------------|
| `tiny` | ~0.07 | 2 | 4 | 1 | Suitable for lightweight tasks and low resource usage. |
| `base` | ~0.14 | 4 | 6 | 2 | Good for basic transcription and smaller workloads. |
| `small` | ~0.46 | 6 | 8 | 4 | Ideal for moderate tasks, offering a balance between performance and accuracy. |
| `medium` | ~1.5 | 8 | 12 | 8 | Recommended for larger tasks with higher accuracy demands. |
| `large-v2` | ~2.88 | 10 | 16 | 10 | Best for high-performance tasks and large-scale transcription. |
| `large-v3` | ~2.88 | 12 | 16+ | 10+ | Highest accuracy and resource usage. Ideal for GPU-accelerated environments. |
> [!TIP]
> For models running on GPU, using CUDA-enabled GPUs with sufficient VRAM is recommended to significantly improve performance. CPU-based inference may require additional RAM and processing time.
> [!WARNING]
> By default, `base`, `base.en`, & `large-v3` models are loaded. Models can be configured from the `backend/Dockerfile`. However, `base` model must not be removed as it is statically configured to be the default model.
## Supported formats
### Import Options:
- Audio: `.mp3`, `.wav`, `.flac`, `.m4a`, etc.
- Video: `.mp4`, `.mkv`, `.avi`, `.mov`, etc.
### Export Options:
- Users can export the results in `.txt`, `.json`, `.srt`, or `.vtt` formats.
## Usage
> [!NOTE]
> Project will run on GPU by default. To run on CPU, use the `docker-compose.cpu.yml` instead
1. Clone this repository and navigate to project folder
```
git clone https://github.com/NotYuSheng/Transcribe-Translate.git
cd Transcribe-Translate
```
2. Build the Docker images:
```
docker-compose build
```
3. Run images
```
docker-compose up -d
```
4. Access webpage from host
```
:8000
```
## Configuration Details
### User Concurrency
The application backend is configured to handle **4 concurrent** users using the `--workers` option in the `backend/Dockerfile`.
```
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000", "--timeout-keep-alive", "600", "--workers", "4"]
```
### Large File Uploads
The app supports file uploads of up to **5GB**. This is configured by setting `client_max_body_size` in the `nginx/nginx.conf`.
```
client_max_body_size 5G;
```
### Timeout Settings
To accommodate large uploads and longer processing times by providing **10 mins** keep alive setting in `backend/Dockerfile` with the following timeout settings in `nginx/nginx.conf`.
```
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000", "--timeout-keep-alive", "600", "--workers", "4"]
```
```
proxy_read_timeout 600s;
proxy_connect_timeout 600s;
proxy_send_timeout 600s;
send_timeout 600s;
```
## Additional Notes
> [!CAUTION]
> Project is intended to be use in a local network by trusted user, therefore there is **no rate limit configured and the project is vulnerable to request floods**. Consider switching to `slowapi` if this is unacceptable.
> [!TIP]
> For transcribing English inputs, `.en` version of the models are recommended