Whisper
Robust Speech Recognition via Large-Scale Weak Supervision, capable of transcribing and translating spoken language.
Whisper is built in Python, distributed under the MIT License, 97.6k GitHub stars from 80 contributors, latest release v20250625.
When to use Whisper
Whisper is listed here as a AI project. The directory calls out High accuracy transcription, Supports multiple languages, Large-scale weak supervision as capabilities associated with it.
Other recorded traits for Whisper include Scalable model architecture, Open-source.
Besides AI, this page also files Whisper under Tools, Development, Data Science.
Whisper compared with
Records in this directory name Google Cloud Speech-to-Text, IBM Watson Speech to Text, Microsoft Azure Speech Services as products people compare with Whisper. That list is editorial metadata, not a claim that Whisper replaces each of them.
Open-source projects that mention Whisper are collected on a separate alternatives page.
What the Whisper stats reflect
GitHub currently shows 97.6k GitHub stars, about 80 contributors, 12.0k forks, 119 open issues, latest tracked release v20250625. Star and activity counts here are a snapshot used as a proxy for community adoption, not a quality score.
Stats refreshed
- Language
- Python
- Latest Release
- v20250625
- License
- MIT License
Our Newsletter
Get new AI tools right in your inbox
Get short emails with useful ai projects, releases, and repos worth watching.
Key features of Whisper
- High accuracy transcription
- Supports multiple languages
- Large-scale weak supervision
- Scalable model architecture
- Open-source
Recorded alternatives to Whisper
Whisper resources
Whisper on GitHub
Frequently asked questions
What is Whisper?
Robust Speech Recognition via Large-Scale Weak Supervision, capable of transcribing and translating spoken language. This directory highlights High accuracy transcription, Supports multiple languages, Large-scale weak supervision.
Is Whisper free to use?
Whisper is published as open source under the MIT License. The directory lists High accuracy transcription, Supports multiple languages, Large-scale weak supervision among its recorded capabilities.
What language is Whisper written in, and what is the latest release?
Whisper is written primarily in Python. The latest release tracked on this page is v20250625.
How widely is Whisper used on GitHub?
Whisper has about 97.6k GitHub stars across about 80 contributors. It also has about 12.0k forks. Those counts are a snapshot of community attention, not a ranking of quality.
What do people compare Whisper with?
This directory records Google Cloud Speech-to-Text, IBM Watson Speech to Text, Microsoft Azure Speech Services as comparison points for Whisper. A longer list of open-source projects that mention Whisper is at https://www.open-source-tools.com/alternatives/whisper.
More AI tools
Graphiti
Graphiti helps to build real-time knowledge graphs tailored for AI agents, enhancing their decision-making and data processing capabilities.
Unstructured
Unstructured is an open-source ETL solution that converts complex documents into structured data for language models, featuring enterprise-grade capabilities like workflow orchestration, document partitioning, enrichment, chunking, and embedding.
Lmnr
Laminar - an open-source all-in-one platform for engineering AI products. Create a data flywheel for your AI applications, with features such as Traces, Evals, Datasets, and Labels. Part of the Y Combinator Summer 2024 batch.
PaddleOCR
PaddleOCR is a powerful and lightweight open source OCR toolkit that enables conversion of images and PDF documents into structured data for AI applications. It supports over 100 languages, making it a versatile bridge between image/PDF content and large language models (LLMs) for a wide range of tasks.
Crawl4AI
Crawl4AI is an open-source and LLM-friendly web crawler and scraper that facilitates efficient data extraction from the web.
Llama
Inference code for Llama models, a versatile solution for running Llama model inferences efficiently.