https://github.com/ankushrathour/speech-to-text-fastapi

Speech to Text using FastAPI, AutoSub and Ffmpeg
https://github.com/ankushrathour/speech-to-text-fastapi

autosub fastapi ffmpeg python3 speech-api speech-recognition speech-to-text

Last synced: 5 months ago
JSON representation

Speech to Text using FastAPI, AutoSub and Ffmpeg

• Host: GitHub
• URL: https://github.com/ankushrathour/speech-to-text-fastapi
• Owner: AnkushRathour
• License: gpl-3.0
• Created: 2024-02-24T09:11:42.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-02-24T10:14:47.000Z (over 1 year ago)
• Last Synced: 2024-12-29T00:10:41.929Z (7 months ago)
• Topics: autosub, fastapi, ffmpeg, python3, speech-api, speech-recognition, speech-to-text
• Language: Python
• Homepage:
• Size: 17.6 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Speech To Text FastAPI

Speech To Text API using [Autosub](https://github.com/agermanidis/autosub), [FastAPI](https://fastapi.tiangolo.com/) and [Ffmpeg](https://ffmpeg.org/).

# Installation

- pip install fastapi

- pip install uvicorn

- pip install autosub

- Install Ffmpeg on your Operation System (Window, Mac, Ubunut) Check Docs for Installation process.

# How to use

[app.py](https://github.com/AnkushRathour/Speech-to-Text-FastAPI/blob/main/app.py) - Generate Transcript from url with media file

Command to start FastAPI server

- uvicorn app:app --host 0.0.0.0 --port 80 --relaod

[main.py](https://github.com/AnkushRathour/Speech-to-Text-FastAPI/blob/main/app.py) - Upload your local audio or video file and generates it transcription.

Command to start

- uvicorn main:app --host 0.0.0.0 --port 80 --relaod