AudioScribe. Turn audio files into written text automatically.

github.com/smaranjitghose/AIAudioTranscriber

@smaranjitghose

Problem

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.

Audience

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.

Market

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.

Pricing

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.

Vaya's read on this project

Problem, audience, market, and the verdict — sign in to see it.

Updates

March 2023

generalize transcript name to audio Mar 30
Update image path for readme. Mar 30
Update get_writer to support OpenAI api Mar 30

January 2023

Removed Redundancy Jan 16
Ignore Model Weights Jan 5
Update Model Choice with local paths and new names, Rearrange Input M… Jan 5
Modify paths using pathlinb Jan 5
Move Model Files inside assets Jan 5
Add Instruction to Download Model Weights Jan 5
Script to Download and Store Model Weights Locally Jan 5
Enabled Git LFS for Model Weights Jan 5
Update README.MD Jan 3

December 2022

Temporarily Disable Trivy Dec 30
Update Docker BuildX Instance Command Dec 30
Update Docker Notes Dec 30
Merge branch 'master' of https://github.com/smaranjitghose/AIAudioTra… Dec 30
Disable multi-system container build Dec 30
Merge pull request #5 from smaranjitghose/imgbot Dec 30
Attempt to fix numpy error Dec 30
Upgrade Python_Debian Layers and reduce size Dec 30