openai

whisper

Python2022–2026

openai / whisper

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

AI & Machine Learning

Explore on GitHub Read Hacker News discussions

114Distinct people

127Mentions

1Explicit recommenders

112.6KGitHub stars

REPOSITORY AT A GLANCE

What to know before exploring

What it is

Robust Speech Recognition via Large-Scale Weak Supervision

GitHub

Where it is used

No documented product use was verified in the last source check.

What people are saying

Use Whisper! It's a fairly small AI speech-to-text model that's great for getting your feet wet with AI libraries. It's extremely precise and easy to get working, I recommend…

smoldesu used a recommendation phrase. One indexed comment matches. This is a phrase match, not a verdict.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

ggml-org/whisper.cpp · linked in 6 of the same discussions
const-me/whisper · linked in 2 of the same discussions

Mentioned in the same Hacker News threads. That is not proof they are substitutes.

This week on Hacker News

Nov 8–Nov 15 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/15/2026, 4:00:59 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by year127 dated mentions

Observed mentions: 2022-09-21 16:35:56 UTC to 2026-10-13 12:39:43 UTC.

* An incomplete calendar period is marked with an outlined bar. Its count is not directly comparable with a full period.

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges

UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
Period	Start (UTC)	End (exclusive, UTC)	Mentions	Submissions	Comments
2022	2022-01-01 00:00:00 UTC	2023-01-01 00:00:00 UTC	36	3	33
2023	2023-01-01 00:00:00 UTC	2024-01-01 00:00:00 UTC	48	4	44
2024	2024-01-01 00:00:00 UTC	2025-01-01 00:00:00 UTC	19	6	13
2025	2025-01-01 00:00:00 UTC	2026-01-01 00:00:00 UTC	20	3	17
2026 (partial)	2026-01-01 00:00:00 UTC	2027-01-01 00:00:00 UTC	4	1	3

What Hacker News says

48 sources

mmh0000·Dec 27, 2023

I don't know how OP does it, but here's how I'd do it: * Generate a transcript by runing Whisper against the podcast audio file: https://github.com/openai/whisper * Upload transcript to ChatGPT and ask it to summarize. * Automate all the above. EDIT: Apparently I'm not keeping up with the times. ChatGPT can directly read/transcribe mp3 files now. Step 1 I guess isn't really needed.

In Ask HN: Favorite Podcast Episodes of 2023?

ipsum2·Nov 24, 2023

Whisper already generates subtitles[0], supporting VTT and SRT so this is just a thin wrapper around that. [0]: https://github.com/openai/whisper/blob/e58f28804528831904c3b...

In Subtitle is now open-source

smoldesu·Nov 21, 2023Recommendation phrase

Use Whisper! It's a fairly small AI speech-to-text model that's great for getting your feet wet with AI libraries. It's extremely precise and easy to get working, I recommend it over pretty much everything else. https://github.com/openai/whisper

In Ask HN: How do you get started with adding voice commands to a computer system?

dijital·Nov 20, 2023

The title doesn't really highlight it but this is using OpenAI's Whisper behind the scenes and can simultaneosly do transcription and diarisation (speaker identification), which is one of the most highly voted discussion topics on the Whisper project: https://github.com/openai/whisper/discussions/264 Very promising for online meetings to have a transcript of what was discussed.

In Turn Speech into Text with Audio Hijack 4.3's New Transcribe Block

fintechie·Nov 19, 2023

> although it does require you to wear headphones so the bot doesn't hear itself and get interrupted. Maybe you can use some sort of speaker identification to sort this out? https://github.com/openai/whisper/discussions/264

In StyleTTS2 – open-source Eleven-Labs-quality Text To Speech

coder543·Nov 16, 2023

v3 only comes in one flavor: large. I don’t think you’re going to have a good time running the large model on a Pi of any kind. The large models are 32x slower than the tiny models, roughly.[0] I just tested, and whisper.cpp on my Pi 4 can transcribe the 30-second a13.wav sample (“make samples” to fetch it) in 18.5 seconds. You can do the math… 32x = 10 minutes transcribe 30 seconds of audio with the large model. Not a good time for most people. The Pi 5 could be 2x to 3x faster. [0]: https://github.com/openai/whisper/blob/main/README.md#availa...

In Federated finetuning of Whisper on Raspberry Pi 5

hiatus·Nov 16, 2023

You can do it live or you can do it from a video file. There are more than just English models as well, though the performance varies by language. https://github.com/openai/whisper

In Saying Goodbye to OpenSubtitles.org API

samber·Nov 7, 2023Submission

Whisper v3

46 points · Open discussion

euazOn·Nov 7, 2023

Do you know if these implementations also support leveraging the M1/M2 GPU, such as shown here? https://github.com/openai/whisper/pull/382

In OpenAI releases Whisper v3, new generation open source ASR model

nshm·Nov 6, 2023

Good improvements for many languages, numbers here https://github.com/openai/whisper/blob/main/language-breakdo...

In OpenAI releases Whisper v3, new generation open source ASR model

modeless·Nov 6, 2023

Whisper V3 is released! https://github.com/openai/whisper/commit/c5d42560760a05584c1... Looks like it's just a new checkpoint for the large model. It would be nice to have updates for the smaller models too. But it'll be easy to integrate with anything using Whisper V2. I'm excited to add it to my local voice AI (https://www.microsoft.com/store/apps/9NC624PBFGB7) I assume ChatGPT voice has been using Whisper V3 and I've noticed that it still has the classic Whisper hallucinations ("Thank you for watching!"), so I guess it's an incremental improvement but not revolutionary.

In New models and developer products

crakenzak·Nov 6, 2023Submission

OpenAI releases Whisper v3, new generation open source ASR model

117 points · Open discussion

GaggiX·Nov 6, 2023

The Whisper V3 model was released open source a few minutes ago: https://github.com/openai/whisper/commit/c5d42560760a05584c1...

In OpenAI DevDay, Opening Keynote Livestream [video]

GaggiX·Nov 6, 2023

Oh nice a new open source Whisper version: https://github.com/openai/whisper/commit/c5d42560760a05584c1...

In OpenAI DevDay, Opening Keynote Livestream [video]

kkielhofner·Nov 2, 2023

Thanks! STT is "just" a very heavily optimized (beyond even faster-whisper) Whisper implementation, so all of those languages[0]. For TTS we now use Coqui, which has a wide range of models with various voices, languages, etc. It even supports Meta MMS which has support for 1,100 languages[1]. [0] - https://github.com/openai/whisper#available-models-and-langu... [1] - https://about.fb.com/news/2023/05/ai-massively-multilingual-...

In Home Assistant 2023.11

Showing the 15 most recent of 48 sources. Enable JavaScript to search and browse every indexed mention.