Transcribe-Translate

Full Page Sample

Host requirements

• Docker: [Installation Guide]
• Docker Compose: [Installation Guide]
• 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

<host-ip>: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