upes-open / OSoc-24-The-Content-Forge

The Content Hub Is a online platform which acts as a all in one solution helping content creators develop and generate short form video image content utilising genai models and cloud to maximize their efficiency and benefit from the ever-growing developments in ai models
GNU Affero General Public License v3.0
0 stars 8 forks source link

Whisper service for Audio processing and Subtitle generation #4

Closed Manav-Khandurie closed 3 days ago

Manav-Khandurie commented 1 week ago

Use FastAPI to create a microservice that communicates with the openai's Whipser model to do audio processing and extract audio in subtitle files

The model used would be available at Whipser Repo

Read the documentation and build the entire Microservice , with appropriate Dockerfiles and API endpoint to host and utilize the service

Additionally store the Audio files in a s3 bucket , Creds will be provided by the lead.

Siddharthaaa21 commented 3 days ago

made a model like, can use s3 bucket as well as the with fastapi since didnt had s3 bucket credentials. shall i?

Manav-Khandurie commented 3 days ago

made a model like, can use s3 bucket as well as the with fastapi since didnt had s3 bucket credentials. shall i?

We have a separate service that will handle working with s3 @Siddharthaaa21