Hacker News

FEBRUARY 28, 2024

A Full Transcript and Slides from the talk "Attacks on Anonymity Systems: The Theory" by Len Sassaman and Roger Dingledine in 2003 - Dicklesworthstone/sassaman_and_dingledine_on_remailers_at_blackhat_2003

62

62

AWS Machine Learning Blog

JUNE 6, 2023

Amazon Transcribe is a speech recognition service that generates transcripts from video and audio files in multiple supported languages and accents. It comes with a rich set of features , including automatic language identification, multi-channel and multi-speaker support, custom vocabularies, and transcript redaction.

65

65

Hacker News

FEBRUARY 24, 2024

A Full Transcript of the Ligthill Debate on AI from 1973, with Introductory Remarks - Dicklesworthstone/the_lighthill_debate_on_ai

AI 65

AI AI 65

Hacker News

NOVEMBER 11, 2023

Easily take an entire YouTube playlist and turn it into high quality transcripts using Whisper. GitHub - Dicklesworthstone/bulk_transcribe_youtube_videos_from_playlist: Easily take an entire YouTube playlist and turn it into high quality transcripts using Whisper.

59

59

AssemblyAI

DECEMBER 15, 2023

Join Us On Discord 🚀 New Punctuation & Casing Model For Real-Time We recently released a significant improvement to our  Punctuation and Truecasing model  for asynchronous transcription.  We've revamped our sample applications to enable previously incompatible integrations to now use this new SDK version.

Python 59

Python AI AI 59

AssemblyAI

SEPTEMBER 13, 2023

In this article, we will be examining one component of virtual meeting platforms: using AI to automatically summarize meeting transcripts. Finally, we will discuss how to automatically summarize meeting transcripts yourself, or how to choose one of the top companies to use to automatically summarize meeting transcripts for you.

AI 52

AI AI Python 52

Analytics Vidhya

AUGUST 22, 2023

This all-in-one multilingual multimodal translation and transcription model is set to redefine language barriers, making cross-lingual conversations a seamless reality. In a revolutionary move towards global communication, the tech giant Meta has unveiled its latest AI model, named SeamlessM4T.

AI 226

AI AI Analytics Analytics 226

Flipboard

JUNE 2, 2023

This article will show you how to use OpenAI's Whisper API to transcribe audio into text. It will also show you how to use it in your own projects and how to integrate it into your data science projects.

Data Science 142

Data Science Python 142

AssemblyAI

SEPTEMBER 14, 2023

More specifically, we’ll walk you through: Creating a cloud recording on zoom Accessing Zoom’s API with your own account Fetching a cloud recording from Zoom’s API Submitting the cloud recording to AssemblyAI for fast, automatic transcription Get your coding fingers ready, and let’s dive in!

Python 59

Python 59

AssemblyAI

DECEMBER 14, 2022

Today, we're excited to announce our new v9 transcription model. Overall Improvements Word Error Rate , or WER, is the primary quantitative metric by which the performance of an automatic transcription model is measured. WER effectively reports the percentage of words in a transcription that differ from what was actually said.

Supervised Learning 52

Supervised Learning AI AI 52

AssemblyAI

APRIL 11, 2023

AI-powered transcription. Source: Screenloop For their customers, intelligent transcription would translate directly into increased productivity and decreased time-to-hire, as it would help cut down on time wasted by tedious manual tasks such as interview transcription, note-taking, and candidate review.

AI 52

AI AI Analytics Analytics 52

Analytics Vidhya

SEPTEMBER 27, 2023

Customer sentiment analysis analyzes customer feedback, such as product reviews, chat transcripts, emails, and call center interactions, to categorize customers into happy, neutral, or unhappy. Introduction Sentiment analysis has revolutionized the way companies understand and respond to customer feedback.

AI 287

AI AI Analytics Analytics 287

Analytics Vidhya

JANUARY 9, 2024

Developed in collaboration with Suno.ai, Parakeet emerges as a formidable player in the realm of speech transcription, boasting capabilities that set it apart in a league of its own. In a recent development for the field of Conversational AI, NVIDIA NeMo has launched Parakeet, its latest series of Automatic Speech Recognition (ASR) models.

Analytics 234

Analytics Analytics AI AI 234

AssemblyAI

MAY 29, 2024

Automatically-generated transcripts from audio and video files are a lot more useful and readable when punctuation, casing, and formatting are added to the transcription result. In this tutorial, you'll explore how to add punctuation, casing, and formatting to your transcripts using the AssemblyAI JavaScript SDK.

59

59

Flipboard

SEPTEMBER 16, 2023

If you've ever had to transcribe an audio file by hand, you know how time-consuming it can be. Luckily, with the advent of machine learning and the …

Machine Learning 87

Machine Learning Machine Learning Computer Science Computer Science 87

Dataconomy

APRIL 26, 2023

is an AI-powered software that provides automatic speech recognition and transcription for audio and video files. uses artificial intelligence and natural language processing to generate accurate and searchable transcripts that you can edit, highlight, comment on, and export. is more than just a transcription tool.

Artificial Intelligence 194

Artificial Intelligence Artificial Intelligence AI AI 194

KDnuggets

JUNE 7, 2023

ChatGPT for Data Science Interview Cheatsheets • Programming Languages for Specific Data Roles • 10 Jupyter Notebook Tips and Tricks for Data Scientists • Revolutionizing Data Analysis with PandasGUI • OpenAI’s Whisper API for Transcription and Translation

Data Science 184

Data Science Data Scientist Data Analysis Data Analysis 184

KDnuggets

OCTOBER 20, 2022

As Speech Recognition has become more accurate than ever, scenarios like dictation and meeting transcription are gaining popularity. Metrics need to evolve with the times and guide the research focus.

Natural Language Processing 226

Natural Language Processing 226

AssemblyAI

MAY 28, 2024

You'll see the profanity-filtered audio transcript printed to the terminal - if you used the default file from above you’ll see the following output printed to the terminal: Filtering profanity from audio and video files is easy as s with AssemblyAI. For this tutorial, you'll be using this example file.

AI 64

AI AI 64

Flipboard

SEPTEMBER 2, 2023

[00:00:00] Adam Grant: Hey everyone, it's Adam Grant. Welcome back to ReThinking, my podcast on the science of what makes us tick. I'm an …

AI 120

AI AI Machine Learning Machine Learning 120

Flipboard

JANUARY 3, 2024

Put the power of an AI PC to work with transcription, music generation and more. As AI PCs debut, one question you’ll be asking yourself is: What can …

AI 150

AI AI Computer Science Computer Science 150

AssemblyAI

APRIL 8, 2024

Transcribe an audio file using Universal-1 By default, all transcriptions use the Best tier, so you’ll always get the highest accuracy without any extra configuration. If you have high-volume transcriptions and looking to reduce costs, or if you need additional language support, we encourage you to try Nano.

102

102

KDnuggets

AUGUST 11, 2022

Check out this video, summary and transcript of a discussion between co:rise co-founder Jake Samuelson and three outstanding ML engineers — Kaushik Rangadurai, Shalvi Mahajan, and Frank Chen — to hear their advice on landing a job in machine learning.

ML 213

ML ML Machine Learning Machine Learning 213

Flipboard

FEBRUARY 4, 2023

Are you looking for Mac software to transcribe audio files into written text files? There are plenty of paid tools, like Otter.ai and Trint, that can cost real money when you start using them too much. But MacWhisper is the free solution the internet has been waiting for. Or, at least, the one I’ve …

Artificial Intelligence 84

Artificial Intelligence Artificial Intelligence Machine Learning Machine Learning 84

AssemblyAI

JANUARY 12, 2024

The GitHub page also provides extensive code examples for using the API, such as for applying different Speech AI models, exporting subtitles, synchronous vs. asynchronous transcriptions, or adding custom spellings.  The SDK is primarily written for Node.js in TypeScript, but is also compatible with other runtimes.

AI 110

AI AI Python Natural Language Processing 110

AWS Machine Learning Blog

APRIL 18, 2024

It uses Amazon Transcribe for speech to text, Knowledge Bases for Amazon Bedrock for contextual queries against your company’s documents and knowledge sources, and Amazon Bedrock models for customizable transcription insights and summaries. The summaries are generated from the transcript by Amazon Bedrock.

AWS 102

AWS Analytics Analytics AI 102

Mlearning.ai

AUGUST 4, 2023

In the era of big data, the ability to process and interpret vast amounts of information quickly is paramount. With the growing importance… Continue reading on MLearning.ai »

Big Data 52

Big Data Big Data ML ML 52

AssemblyAI

MAY 22, 2024

Create a file called main.py , and then import the assemblyai package and specify the path to the audio file you want to filter profanity from: import assemblyai as aai # replace with local filepath or your remote file audio_url = "[link] Next, we create an aai.TranscriptionConfig object, in which we specify the settings for our transcription.

Python 64

Python Artificial Intelligence Artificial Intelligence AI 64

Hacker News

FEBRUARY 18, 2024

Download subtitles is a free web application that can download subtitles directly from Youtube

76

76

Mlearning.ai

AUGUST 1, 2023

One of the fascinating applications that draw your attention is speech recognition. It’s not just because of its increasing use in modern… Continue reading on MLearning.ai »

Python 52

Python ML ML 52

AWS Machine Learning Blog

MARCH 1, 2024

The automated chatbot designer uses ML to provide an initial bot design that you can then refine and launch conversational experiences faster based on your current call transcripts. However, the automated chatbot designer requires transcripts to be in a certain format that is not aligned to Genesys Cloud transcript exports.

AWS 88

AWS ML ML Analytics 88

AssemblyAI

APRIL 15, 2024

Transcribe an audio file using Universal-1 All transcriptions use the Best class of models by default, so you’ll always get the highest accuracy without any extra configuration. Use the following code to transcribe an audio file from a URL using Best: Transcript transcript = client.transcripts().transcribe(

AI 64

AI AI 64

AWS Machine Learning Blog

MAY 30, 2024

In parallel, the system extracts audio transcription from the uploaded content using Amazon Transcribe. Semantic search – Powered by the Amazon Titan Text Embeddings model , generated based on transcription and image metadata extracted at the frame level. The transcription of the video is within the tag.

AWS 106

AWS AI AI ML 106

Dataconomy

APRIL 8, 2024

The report began with a focus on OpenAI, which, in its quest for adequate training data, is said to have created the Whisper audio transcription model. This initiative allowed for the transcription of more than a million hours of YouTube content to advance the development of GPT-4, their latest and most sophisticated large language model.

AI 103

AI AI Machine Learning Machine Learning 103

AssemblyAI

AUGUST 3, 2023

and add the following code for interacting with the AssemblyAI API: /** * The parameters to create a Transcript in the AssemblyAI API. string; } /** * The transcript object returned by the AssemblyAI API. * Then, update the Env interface in the worker.ts You can add more properties to this type if you need them.

Database 97

Database 97

Flipboard

DECEMBER 15, 2023

You don't need to pay a premium for a quality transcription service. Here's a roundup of our favorite free platforms. As artificial intelligence …

Artificial Intelligence 122

Artificial Intelligence Artificial Intelligence AI AI 122

AssemblyAI

JANUARY 8, 2024

build(); Transcript transcript = client.transcripts().transcribe( transcribe( "[link] ); System.out.println(transcript); You can also transcribe a local file, as shown here. Transcript transcript = client.transcripts().transcribe(new prompt("Summarize this transcript.").transcriptIds(List.of(transcript.getId())).build());

72

72