Skip to main content

I used OpenAI’s new tech to transcribe audio right on my laptop

Illustration of a series of blue microphones on a teal background.
The benefits of AI without the drawbacks of the cloud. | Kristen Radtke / The Verge; Getty Images

OpenAI, the company behind image-generation and meme-spawning program DALL-E and the powerful text autocomplete engine GPT-3, has launched a new, open-source neural network meant to transcribe audio into written text (via TechCrunch). It’s called Whisper, and the company says it “approaches human level robustness and accuracy on English speech recognition” and that it can also automatically recognize, transcribe, and translate other languages like Spanish, Italian, and Japanese.

As someone who’s constantly recording and transcribing interviews, I was immediately hyped about this news — I thought I’d be able to write my own app to securely transcribe audio right from my computer. While cloud-based services like Otter.ai and Trint work for most things and are relatively secure, there are just some interviews where I, or my sources, would feel more comfortable if the audio file stayed off the internet.

Using it turned out to be even easier than I’d imagined; I already have Python and various developer tools set up on my computer, so installing Whisper was as easy as running a single Terminal command. Within 15 minutes, I was able to use Whisper to transcribe a test audio clip that I’d recorded. For someone relatively tech-savvy who didn’t already have Python, FFmpeg, Xcode, and Homebrew set up, it’d probably take closer to an hour or two. There is already someone working on making the process much simpler and user-friendly, though, which we’ll talk about in just a second.

Command-line apps obviously aren’t for everyone, but for something that’s doing a relatively complex job, Whisper’s very easy to use.

While OpenAI definitely saw this use case as a possibility, it’s pretty clear the company is mainly targeting researchers and developers with this release. In the blog post announcing Whisper, the team said its code could “serve as a foundation for building useful applications and for further research on robust speech processing” and that it hopes “Whisper’s high accuracy and ease of use will allow developers to add voice interfaces to a much wider set of applications.” This approach is still notable, however — the company has limited access to its most popular machine-learning projects like DALL-E or GPT-3, citing a desire to “learn more about real-world use and continue to iterate on our safety systems.”

Image showing a text file with the transcribed lyrics for Yung Gravy’s song “Betty (Get Money).” The transcription contains many inaccuracies.
The text files Whisper produces aren’t exactly the easiest to read if you’re using them to write an article, either.

There’s also the fact that it’s not exactly a user-friendly process to install Whisper for most people. However, journalist Peter Sterne has teamed up with GitHub developer advocate Christina Warren to try and fix that, announcing that they’re creating a “free, secure, and easy-to-use transcription app for journalists” based on Whisper’s machine learning model. I spoke to Sterne, and he said that he decided the program, dubbed Stage Whisper, should exist after he ran some interviews through it and determined that it was “the best transcription I’d ever used, with the exception of human transcribers.”

I compared a transcription generated by Whisper to what Otter.ai and Trint put out for the same file, and I would say that it was relatively comparable. There were enough errors in all of them that I would never just copy and paste quotes from them into an article without double-checking the audio (which is, of course, best practice anyway, no matter what service you’re using). But Whisper’s version would absolutely do the job for me; I can search through it to find the sections I need and then just double-check those manually. In theory, Stage Whisper should perform exactly the same since it’ll be using the same model, just with a GUI wrapped around it.

Sterne admitted that tech from Apple and Google could make Stage Whisper obsolete within a few years — the Pixel’s voice recorder app has been able to do offline transcriptions for years, and a version of that feature is starting to roll out to some other Android devices, and Apple has offline dictation built into iOS (though currently there’s not a good way to actually transcribe audio files with it). “But we can’t wait that long,” Sterne said. “Journalists like us need good auto-transcription apps today.” He hopes to have a bare-bones version of the Whisper-based app ready in two weeks.

To be clear, Whisper probably won’t totally obsolete cloud-based services like Otter.ai and Trint, no matter how easy it is to use. For one, OpenAI’s model is missing one of the biggest features of traditional transcription services: being able to label who said what. Sterne said Stage Whisper probably wouldn’t support this feature: “we’re not developing our own machine learning model.”

And while you’re getting the benefits of local processing, you’re also getting the drawbacks. The main one is that your laptop is almost certainly significantly less powerful than the computers a professional transcription service is using. For example, I fed the audio from a 24-minute-long interview into Whisper, running on my M1 MacBook Pro; it took around 52 minutes to transcribe the whole file. (Yes, I did make sure it was using the Apple Silicon version of Python instead of the Intel one.) Otter spat out a transcript in less than eight minutes.

OpenAI’s tech does have one big advantage, though — price. The cloud-based subscription services will almost certainly cost you money if you’re using them professionally (Otter has a free tier, but upcoming changes are going to make it less useful for people who are transcribing things frequently), and the transcription features built-into platforms like Microsoft Word or the Pixel require you to pay for separate software or hardware. Stage Whisper — and Whisper itself— is free and can run on the computer you already have.

Again, OpenAI has higher hopes for Whisper than it being the basis for a secure transcription app — and I’m very excited about what researchers end up doing with it or what they’ll learn by looking at the machine learning model, which was trained on “680,000 hours of multilingual and multitask supervised data collected from the web.” But the fact that it also happens to have a real, practical use today makes it all the more exciting.



Source: The Verge

Popular posts from this blog

FCC approves broadband 'nutrition labels' to help you shop for internet

The FCC is pushing nutrition labels for internet providers. What you need to know The FCC has voted to move forward with new rules for ISPs to display nutrition labels. The proposed rulemaking would mandate ISPs to display relevant speed and pricing information to consumers. This should make it easier for consumers to make an informed decision on their broadband. The FCC voted unanimously on a plan that would allow consumers to make better decisions about their broadband internet. The proposal will require internet service providers (ISPs) - including many of the best wireless carriers in the U.S. — to display "nutrition labels" that display relevant service information for consumers at point-of-sale. This includes internet speeds, allowances, and clear information on rates. "If you walk into any grocery store and pull boxes of cereal from the shelves, you can easily compare calories and carbohydrates," FCC Chair Jessica Rosenworcel said in a statemen

Slack’s new integration deal with AWS could also be about tweaking Microsoft

Slack and Amazon announced a big integration late yesterday afternoon. As part of the deal, Slack will use Amazon Chime for its call feature, while reiterating its commitment to use AWS as its preferred cloud provider to run its infrastructure. At the same time, AWS has agreed to use Slack for internal communications. Make no mistake, this is a big deal as the SaaS communications tool increases its ties with AWS, but this agreement could also be about slighting Microsoft and its rival Teams product by making a deal with a cloud rival. In the past Slack CEO Stewart Butterfield has had choice words for Microsoft saying the Redmond technology giant sees his company as an “existential threat.” Whether that’s true or not — Teams is but one piece of a huge technology company — it’s impossible not to look at the deal in this context. Aligning more deeply with AWS sends a message to Microsoft, whose Azure infrastructure services compete with AWS. Butterfield didn’t say that of course

Yandex spins out self-driving car unit from its Uber JV, invests $150M into newco

Self-driving cars are still many years away from becoming a ubiquitous reality, but today one of the bigger efforts to build and develop them is taking a significant step out as part of its strategy to be at the forefront for when they do. Yandex — the publicly-traded Russian tech giant that started as a search engine but has expanded into a number of other, related areas (similar to US counterpart Google) — today announced that it is spinning out its self-driving car unit from MLU BV — a ride-hailing and food delivery joint venture it operates in partnership with Uber. The move comes amid reports that Yandex and Uber were eyeing up an IPO for MLU  last year. At the time, the JV was estimated to be valued at around $7.7 billion. It’s not clear how those plans will have been impacted in recent months, with COVID-19 putting huge pressure on ride-hailing and food-delivery businesses globally, and IPOs generally down compared to a year ago. In that context, spinning out the unit could

Elon Musk sends yet another notice trying to terminate the Twitter deal

Kristen Radtke / The Verge; Getty Images Elon Musk has sent a third letter to Twitter attempting to terminate his $44 billion acquisition of the company . Musk’s legal team cited Twitter’s multimillion dollar severance payment to former security chief and whistleblower Peiter Zatko as a violation of the merger agreement and a reason to end the deal. The letter, dated September 9th, was sent to Twitter’s chief legal officer Vijaya Gadde, and was included in a filing Twitter made with the SEC on Friday (which you can read at the bottom of this article). Last month, Zatko made headlines by accusing Twitter of misleading investors about the number of bots on the service, failing to delete users’ data, and having poor security practices, among other things. Musk jumped on the accusations, citing them in his second termination letter and subpoenaing Zatko to testify in the lawsuit. Zatko was set to be deposed on Friday. Elon Musk sent his first letter of termination in July , say