There are 6 repositories under aws-transcribe topic.
speech to text benchmark framework
Amazon Transcribe Live Call Analytics (LCA) Sample Solution
As of August 30, 2023, this AWS Solution is no longer available. Existing deployments will continue to run. The functionality provided by Content Analysis on AWS will be superseded with functionality in Media2Cloud on AWS and Content Localization on AWS. We encourage you to explore these solutions.
This is a simple utility script to convert the Amazon Transcribe .json transcript into a more readable transcript.
An editor for speech-to-text transcripts such as AWS Transcribe and Mozilla DeepSpeech
A simple UI for Amazon Transcribe
A simple AWS demo utilises Amazon Transcribe to convert audio to text and analyse.
An example application using Media Streams and Amazon Transcribe
AI based health checkup web tool
Won 2nd prize in HackUIET hackathon and best project in AI theme
AWS Transcribe evaluation pipeline: bulk-process audio files and view the results
Example python scripts to evaluate various ASR methods
Cloud Audio Translator automatically converts spoken language into text, translates it, and generates speech in the target language using cloud services.
Using AWS Transcribe service, take the JSON output and output HTML into a nice conversational format for easy posting to a blog.
Apna Doctor is an AI based Health Check-Up Web Application
Project developed for the Cloud Computing 2020.1 class. We built a service to add translated subtitles to videos using AWS services.
Shows how to use the Amazon Transcribe API to transcribe a phone conversation recorded with the Nexmo Voice API.
Developing a tool to convert audio calls into structured documents as meeting minutes that can be referred to by the host.
Implement a photo album web application, that can be searched using natural language through both text and voice. Services on AWS: Lex, ElasticSearch, and Rekognition to create an intelligent search layer to query your photos for people, objects, actions, landmarks and more.
Sample serverless application for speech to speech translations
Exemplos para utilização de plataforma de Machine Learning no modelo SaaS como alternativa para aceleração de funcionalidades baseadas em AI em produtos digitais.
Speech Sentiment Analyser is a ML & AI based tool to help analyse the user sentiment in an audio file
Generate translations for transcripts your videos into many languages automatically, using the power of AWS Cloud Computing technologies (Amazon Web Services) you can enjoy in your favorite language and with the control of each time section the content of the video . A perfect way to avoid missing relevant data from your multimedia content.
A FastAPI based chatbot server using OpenAI to respond to textual and audio queries.
The program will transcribe the voice to text, translate the text to the target language, and then convert the text to speech.
An AI web application designed to transcribe videos with near-human accuracy, offering the option to add captions or voice-overs in numerous languages.
Quick Captions is an innovative AI-powered tool that revolutionizes the way you add captions to your videos.
:door: Construindo API com os serviços AWS
Extracting text,form,table using Textract
Audio (.mp3) -> AI Generated Images (work in progress)
AWS Lex, ElasticSearch, Rekognition and CloudFormation
Hiring Hackathon project: an audio transcription software that allows users to upload audio or video files to create a transcript for commenting in real time.
[Backend] 딥러닝 기반 일치율 수식을 이용한 유튜브 콘텐츠 필터링
It is a scalable google photos clone where you can use your voice to search photos based on objects contained in them.
🕵️♂️ Personally Identifiable Information (PII) Detection and Redaction for Voice Audio Files Stored in S3 and AWS Transcribe