Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

We found a hack to make Whisper transcribe into *any* language (not just English)! ⚡️ This is an EXPERIMENTAL one-step feature: enter your audio as input, and get a transcription in another language. 🔥 Check it out here:

74,525 Aufrufe • vor 3 Jahren •via X (Twitter)

10 Kommentare

Profilbild von Vaibhav (VB) Srivastav
Vaibhav (VB) Srivastavvor 3 Jahren

Quick caveat: It's a task that the model isn't explicitly trained on, so test it thoroughly before us 🤗 We'll run more benchmarks this week and share our findings soon! Help us test it better? :)

Profilbild von Vaibhav (VB) Srivastav
Vaibhav (VB) Srivastavvor 3 Jahren

The audio snippet was taken from "Stupid People" comedy routine by Bill Engvall The video was generated via @mhollemans's brilliant Word-level timestamps space:

Profilbild von Eklavya
Eklavyavor 3 Jahren

It could already transcribe into 96 languages. You meant translate.

Profilbild von Vaibhav (VB) Srivastav
Vaibhav (VB) Srivastavvor 3 Jahren

Ha! Semantics - in this case we literally force it to transcribe into a target language. So, technically you can say it is translating! Whisper traditionally only translates from language “X” into English.

Profilbild von Ondřej Plátek
Ondřej Plátekvor 3 Jahren

Cool work! You might also like the work of my colleagues which work on streaming ASR/translation

Profilbild von Kolin Koehl
Kolin Koehlvor 3 Jahren

@altryne have you tried this?

Profilbild von VoiceSparks
VoiceSparksvor 3 Jahren

Thats the way Whisper (not the translation api) works. If you specify a language and speak in another it translates to the specified language. Yes, it's undocumented, but what "hack" do you mean?

Profilbild von Vaibhav (VB) Srivastav
Vaibhav (VB) Srivastavvor 3 Jahren

In my experience those results were quite suboptimal and didn’t quite result in usable transcriptions. With better decoding strategy those issues can be alleviated a bit. So the hack is more so of using contrastive search with Whisper to enable such use cases. Will run more tests soon!

Profilbild von Rober Dam
Rober Damvor 3 Jahren

When you selected portuguese and speak spanish the 2022 original versión do a very good translation, undocumented feature?

Profilbild von Vaibhav (VB) Srivastav
Vaibhav (VB) Srivastavvor 3 Jahren

Yess! Quite possible - although the accuracy of the transcriptions still needs to be checked. I’ve found it to loose context if not used with the right generation strategy! 🤗

Ähnliche Videos