okd/transcripcion-whisper
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Subida de código

Browse Source
This commit is contained in:
Root
2025-05-30 19:09:28 +02:00
parent 31208a52ba
commit faa7458439
32 changed files with 1375 additions and 70 deletions
Download Patch File Download Diff File Expand all files Collapse all files

134
README.md
View File

@@ -1,93 +1,87 @@
# docker-whisper
# Sistema Distribuido de Transcripción con Whisper
Este proyecto implementa un sistema distribuido para la transcripción de archivos de audio utilizando el modelo Whisper de OpenAI. El sistema divide los archivos de audio en segmentos más pequeños (de 5 minutos), procesa estos segmentos en paralelo utilizando múltiples contenedores, y luego unifica las transcripciones para generar un archivo de subtítulos.
## Arquitectura del Sistema
## Getting started
El sistema está compuesto por cuatro tipos de componentes principales:
To make it easy for you to get started with GitLab, here's a list of recommended next steps.
1. **Receptor (Receiver)**: Monitorea el directorio de entrada para nuevos archivos de audio y los envía a RabbitMQ para su procesamiento.
2. **Particionador (Splitter)**: Divide los archivos de audio en segmentos de 5 minutos.
3. **Procesadores (Processors)**: Transcriben los segmentos de audio utilizando Whisper (7 contenedores en paralelo).
4. **Unificador (Unifier)**: Recopila todas las transcripciones, las ordena y genera un archivo final de subtítulos (.srt).
Already a pro? Just edit this README.md and make it your own. Want to make it easy? [Use the template at the bottom](#editing-this-readme)!
## Requisitos previos
## Add your files
- Docker
- Docker Compose
- [ ] [Create](https://docs.gitlab.com/ee/user/project/repository/web_editor.html#create-a-file) or [upload](https://docs.gitlab.com/ee/user/project/repository/web_editor.html#upload-a-file) files
- [ ] [Add files using the command line](https://docs.gitlab.com/topics/git/add_files/#add-files-to-a-git-repository) or push an existing Git repository with the following command:
## Estructura del proyecto
```
cd existing_repo
git remote add origin http://gitlab.local/root/docker-whisper.git
git branch -M main
git push -uf origin main
whisper-distributed/
├── docker-compose.yml # Definición de los servicios
├── input/ # Directorio para colocar los archivos de audio a transcribir
├── output/ # Directorio donde se guardarán los subtítulos generados
├── shared/ # Directorio compartido para almacenamiento temporal
├── processor/ # Código del procesador Whisper
│ ├── app.py
│ └── Dockerfile
├── receiver/ # Código del receptor
│ ├── app.py
│ └── Dockerfile
├── splitter/ # Código del particionador
│ ├── app.py
│ └── Dockerfile
└── unifier/ # Código del unificador
├── app.py
└── Dockerfile
```
## Integrate with your tools
## Uso del sistema
- [ ] [Set up project integrations](http://gitlab.local/root/docker-whisper/-/settings/integrations)
1. **Preparación**:
```bash
docker-compose build
```
## Collaborate with your team
2. **Iniciar el sistema**:
```bash
docker-compose up -d
```
- [ ] [Invite team members and collaborators](https://docs.gitlab.com/ee/user/project/members/)
- [ ] [Create a new merge request](https://docs.gitlab.com/ee/user/project/merge_requests/creating_merge_requests.html)
- [ ] [Automatically close issues from merge requests](https://docs.gitlab.com/ee/user/project/issues/managing_issues.html#closing-issues-automatically)
- [ ] [Enable merge request approvals](https://docs.gitlab.com/ee/user/project/merge_requests/approvals/)
- [ ] [Set auto-merge](https://docs.gitlab.com/user/project/merge_requests/auto_merge/)
3. **Uso**:
- Coloca los archivos de audio que deseas transcribir en el directorio `input/`.
- El sistema detectará automáticamente los archivos y comenzará a procesarlos.
- Los subtítulos resultantes se guardarán en el directorio `output/` con el formato `nombre_original_transcription.srt`.
## Test and Deploy
4. **Monitoreo de logs**:
```bash
docker-compose logs -f
```
Use the built-in continuous integration in GitLab.
5. **Detener el sistema**:
```bash
docker-compose down
```
- [ ] [Get started with GitLab CI/CD](https://docs.gitlab.com/ee/ci/quick_start/)
- [ ] [Analyze your code for known vulnerabilities with Static Application Security Testing (SAST)](https://docs.gitlab.com/ee/user/application_security/sast/)
- [ ] [Deploy to Kubernetes, Amazon EC2, or Amazon ECS using Auto Deploy](https://docs.gitlab.com/ee/topics/autodevops/requirements.html)
- [ ] [Use pull-based deployments for improved Kubernetes management](https://docs.gitlab.com/ee/user/clusters/agent/)
- [ ] [Set up protected environments](https://docs.gitlab.com/ee/ci/environments/protected_environments.html)
## Flujo de trabajo
***
1. El **receptor** detecta un nuevo archivo de audio en el directorio `input/` y lo envía a la cola `audio_split_queue`.
2. El **particionador** recibe el archivo, lo divide en segmentos de 5 minutos y envía cada segmento a la cola `audio_process_queue`.
3. Los **procesadores** (7 contenedores) reciben los segmentos, los transcriben utilizando Whisper y envían las transcripciones a la cola `text_unify_queue`.
4. El **unificador** recopila todas las transcripciones de un mismo archivo, las ordena según su posición original y genera un archivo de subtítulos en formato SRT.
# Editing this README
## Configuración
When you're ready to make this README your own, just edit this file and use the handy template below (or feel free to structure it however you want - this is just a starting point!). Thanks to [makeareadme.com](https://www.makeareadme.com/) for this template.
El sistema viene configurado con valores predeterminados, pero se pueden ajustar varios parámetros:
## Suggestions for a good README
- **Tamaño de los segmentos**: Por defecto, 5 minutos. Se puede modificar en `splitter/app.py` (variable `SEGMENT_DURATION_MS`).
- **Modelo de Whisper**: Por defecto, "base". Se puede cambiar a "tiny", "small", "medium" o "large" en `processor/app.py` (variable `WHISPER_MODEL`).
- **Número de procesadores**: Se pueden agregar o quitar procesadores modificando el archivo `docker-compose.yml`.
Every project is different, so consider which of these sections apply to yours. The sections used in the template are suggestions for most open source projects. Also keep in mind that while a README can be too long and detailed, too long is better than too short. If you think your README is too long, consider utilizing another form of documentation rather than cutting out information.
## Notas
## Name
Choose a self-explaining name for your project.
## Description
Let people know what your project can do specifically. Provide context and add a link to any reference visitors might be unfamiliar with. A list of Features or a Background subsection can also be added here. If there are alternatives to your project, this is a good place to list differentiating factors.
## Badges
On some READMEs, you may see small images that convey metadata, such as whether or not all the tests are passing for the project. You can use Shields to add some to your README. Many services also have instructions for adding a badge.
## Visuals
Depending on what you are making, it can be a good idea to include screenshots or even a video (you'll frequently see GIFs rather than actual videos). Tools like ttygif can help, but check out Asciinema for a more sophisticated method.
## Installation
Within a particular ecosystem, there may be a common way of installing things, such as using Yarn, NuGet, or Homebrew. However, consider the possibility that whoever is reading your README is a novice and would like more guidance. Listing specific steps helps remove ambiguity and gets people to using your project as quickly as possible. If it only runs in a specific context like a particular programming language version or operating system or has dependencies that have to be installed manually, also add a Requirements subsection.
## Usage
Use examples liberally, and show the expected output if you can. It's helpful to have inline the smallest example of usage that you can demonstrate, while providing links to more sophisticated examples if they are too long to reasonably include in the README.
## Support
Tell people where they can go to for help. It can be any combination of an issue tracker, a chat room, an email address, etc.
## Roadmap
If you have ideas for releases in the future, it is a good idea to list them in the README.
## Contributing
State if you are open to contributions and what your requirements are for accepting them.
For people who want to make changes to your project, it's helpful to have some documentation on how to get started. Perhaps there is a script that they should run or some environment variables that they need to set. Make these steps explicit. These instructions could also be useful to your future self.
You can also document commands to lint the code or run tests. These steps help to ensure high code quality and reduce the likelihood that the changes inadvertently break something. Having instructions for running tests is especially helpful if it requires external setup, such as starting a Selenium server for testing in a browser.
## Authors and acknowledgment
Show your appreciation to those who have contributed to the project.
## License
For open source projects, say how it is licensed.
## Project status
If you have run out of energy or time for your project, put a note at the top of the README saying that development has slowed down or stopped completely. Someone may choose to fork your project or volunteer to step in as a maintainer or owner, allowing your project to keep going. You can also make an explicit request for maintainers.
- El modelo "base" de Whisper ofrece un buen equilibrio entre precisión y velocidad. Los modelos más grandes (como "medium" o "large") son más precisos pero requieren más recursos.
- Para archivos muy largos, el sistema puede tardar bastante tiempo en procesarlos, especialmente con modelos grandes.
- Asegúrate de tener suficiente espacio en disco para los archivos temporales.