# Whisper

An open-source automatic speech recognition system released by OpenAI in September 2022, trained on 680,000 hours of multilingual audio and widely adopted for transcription, captioning, and voice-interface applications.

Whisper is an automatic [speech-recognition](https://www.wikiprompt.org/wiki/speech-recognition) system released by [openai](https://www.wikiprompt.org/wiki/openai) in September 2022 as an open-source model, with both code and trained weights made publicly available. Unlike most of OpenAI's later releases, Whisper was published with a detailed technical paper describing its training data and methodology, making it one of the more transparent releases from a major AI lab during this period.

## Training and architecture

Whisper is a [transformer](https://www.wikiprompt.org/wiki/transformer)-based encoder-decoder model trained in a largely supervised, weakly labeled fashion on 680,000 hours of audio collected from the web, paired with corresponding transcripts. Roughly a third of that audio was non-English, spanning around 100 languages, and a portion of the training data consisted of translation pairs, giving the model built-in speech-to-text translation capability alongside transcription. This scale and diversity of weakly supervised data was a deliberate contrast to earlier speech recognition systems trained on smaller, more curated academic datasets, echoing broader findings in the field about [scaling](https://www.wikiprompt.org/wiki/scaling-laws) and data diversity improving robustness. The model was released in several sizes, from a lightweight "tiny" version suitable for on-device use to a large model offering the highest accuracy, an approach later followed by v2 and v3 updates that improved performance in several languages.

## Adoption and impact

Because Whisper's weights were released under a permissive open license, it was rapidly integrated into a wide range of third-party products and open-source projects, including meeting transcription tools, subtitle generators, voice assistants, and accessibility software. Its robustness to accents, background noise, and technical vocabulary, relative to prior commercial ASR systems, made it a common default choice for developers building on [natural-language-processing](https://www.wikiprompt.org/wiki/natural-language-processing) pipelines that needed a speech-to-text front end. Whisper also became a component in larger multimodal and voice-interaction systems, feeding transcribed text into downstream [large language models](https://www.wikiprompt.org/wiki/large-language-model) for voice assistants and call-center automation, and its transcripts have been used as a source of training data for other audio and speech projects.

The model's release contributed to a broader trend of foundation-model style [open-weights](https://www.wikiprompt.org/wiki/open-weights) releases from major labs even as those same labs kept their flagship generative models closed, a pattern also seen with [clip](https://www.wikiprompt.org/wiki/clip) a year earlier. Because it lowered the cost of building transcription and translation features, Whisper was frequently cited as a factor accelerating experimentation with voice-driven AI applications, including early integrations feeding into [text-to-speech](https://www.wikiprompt.org/wiki/text-to-speech) and [voice-cloning](https://www.wikiprompt.org/wiki/voice-cloning) pipelines for dubbing and localization products, and it remains widely used as a benchmark and backbone in academic and industry speech research as of 2025.

## Limitations

Whisper is not without weaknesses: it can hallucinate text that was never spoken, particularly during silences or non-speech audio, a failure mode related to but distinct from the broader [hallucination](https://www.wikiprompt.org/wiki/hallucination) problem seen in generative language models. Accuracy also varies substantially across languages, with lower-resource languages showing higher error rates than English and other well-represented languages in its training data, and researchers have documented cases of the model inserting fabricated phrases into medical and other high-stakes transcripts, prompting caution about unsupervised use in sensitive contexts.

---
Source: https://www.wikiprompt.org/wiki/whisper
License: CC BY-SA 4.0 (https://creativecommons.org/licenses/by-sa/4.0/)
Last updated: 2026-09-02T20:32:47.626152+00:00