openai/whisper

Robust Speech Recognition via Large-Scale Weak Supervision

#Speech to text

Python

110.9k

13.6k

84 contributors

MIT License

FeaturedAdvertise to 180K+ monthly visitors

Give Al Agents a Deeper Understanding of Your Codebase with a Code Graph

Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

Control what AI can do before it acts

Momentum

How fast openai/whisper is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Aug 20 – Oct 19, 2026

Stars +3,242 in 61 days

108

Forks +509 in 61 days

20

Merged PRs 1 in 61 days

1

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Aug 20Aug 28Sep 5Sep 13Sep 21Sep 29Oct 7Oct 15

Stars, forks, merged pull requests and Trendshift Trending rank, by day
Day	Stars gained	Forks gained	Merged PRs
Thu, Aug 20, 2026	+46	+5	0
Fri, Aug 21, 2026	+72	+11	0
Sat, Aug 22, 2026	+41	+6	0
Sun, Aug 23, 2026	+44	+8	0
Mon, Aug 24, 2026	+48	+12	0
Tue, Aug 25, 2026	+46	+7	0
Wed, Aug 26, 2026	+48	+6	0
Thu, Aug 27, 2026	+51	+7	0
Fri, Aug 28, 2026	+53	+4	0
Sat, Aug 29, 2026	+45	+6	0
Sun, Aug 30, 2026	+34	+9	0
Mon, Aug 31, 2026	+62	+8	1
Tue, Sep 1, 2026	+59	+6	0
Wed, Sep 2, 2026	+48	+7	0
Thu, Sep 3, 2026	+36	+5	0
Fri, Sep 4, 2026	+75	+5	0
Sat, Sep 5, 2026	+86	+17	0
Sun, Sep 6, 2026	+94	+20	0
Mon, Sep 7, 2026	+88	+7	0
Tue, Sep 8, 2026	+51	+14	0
Wed, Sep 9, 2026	+35	+6	0
Thu, Sep 10, 2026	+58	+4	0
Fri, Sep 11, 2026	+55	+6	0
Sat, Sep 12, 2026	+43	+13	0
Sun, Sep 13, 2026	+69	+6	0
Mon, Sep 14, 2026	+85	+11	0
Tue, Sep 15, 2026	+79	+19	0
Wed, Sep 16, 2026	+36	+12	0
Thu, Sep 17, 2026	+73	+7	0
Fri, Sep 18, 2026	+48	+5	0
Sat, Sep 19, 2026	+30	+8	0
Sun, Sep 20, 2026	+38	+12	0
Mon, Sep 21, 2026	+35	+6	0
Tue, Sep 22, 2026	+41	+4	0
Wed, Sep 23, 2026	+37	+4	0
Thu, Sep 24, 2026	+38	+5	0
Fri, Sep 25, 2026	+42	+3	0
Sat, Sep 26, 2026	+22	+6	0
Sun, Sep 27, 2026	+30	+6	0
Mon, Sep 28, 2026	+49	+9	0
Tue, Sep 29, 2026	+50	+4	0
Wed, Sep 30, 2026	+54	+8	0
Thu, Oct 1, 2026	+44	+8	0
Fri, Oct 2, 2026	+32	+5	0
Sat, Oct 3, 2026	+35	+8	0
Sun, Oct 4, 2026	+56	+14	0
Mon, Oct 5, 2026	+30	+5	0
Tue, Oct 6, 2026	+50	+6	0
Wed, Oct 7, 2026	+58	+9	0
Thu, Oct 8, 2026	+49	+2	0
Fri, Oct 9, 2026	+78	+16	0
Sat, Oct 10, 2026	+55	+10	0
Sun, Oct 11, 2026	+38	+4	0
Mon, Oct 12, 2026	+58	+12	0
Tue, Oct 13, 2026	+73	+16	0
Wed, Oct 14, 2026	+43	+11	0
Thu, Oct 15, 2026	+80	+10	0
Fri, Oct 16, 2026	+108	+14	0
Sat, Oct 17, 2026	+81	+10	0
Sun, Oct 18, 2026	+54	+14	0
Mon, Oct 19, 2026	+46	+1	0
Total	+3,242	+509	1

#1 on the list
Rank that day
Not trending

Mentions and achievements

Where people are talking about openai/whisper, and every badge it has earned

Oct 181 post
- 宝藏GitHub 仓库你一定要收藏，这10 个 GitHub 仓库，star 加起来 69 万以上。一步一个工具，1 小时的长视频拆成一批竖屏成片。 1. yt-dlp 把长视频和音轨从大多数平台拉下来。 2. Whisper 在本机上，把说出来的话转成文字。 3. WhisperX 给到每个词的时间点，也标出是谁在说，字幕能压在那个词上。 4. Ollama…
  Read full on X, posted by @0xGGbond66
  @0xGGbond66 · x.com
Oct 172 posts
- 簡直太誇張了！這 15 個 GitHub repo，可以直接拼出一套 AI Video / Motion Design 工作流！ 1. Remotion 用 React 寫影片，scene、transition、動畫和 render 都能程式化。 2. Excalidraw 先畫 storyboard、鏡頭移動和 scene sequence。 3. Penpot 做 layout、style…
  Read full on X, posted by @kangxiaile
  @kangxiaile · x.com
- 🚨 10 个 GitHub 仓库，真该被“封杀” （它们每年悄悄干掉大公司超过 500 亿美元的收入）先收藏。 1. yt-dlp YouTube、X、TikTok、Instagram 等平台的视频，随便下。 YouTube Premium 每月收 14 美元，干的事还没它多。它完全免费。仓库 → 2. Ollama 在笔记本上直接跑 GPT-4 级别的模型，没有 API 费用。…
  Read full on X, posted by @AIExplorerTim
  @AIExplorerTim · x.com
Oct 162 posts4 posts
- 1. Ollama: run AI models on your own laptop. Private, offline, no API bill.
  Read full on X, posted by @ScaleWthAI
  @ScaleWthAI · x.com
- 4. open-sora → (29.9k⭐) open video maker run them in one app 5. comfyui → (137.7k⭐) drag-and-drop boxes, runs on your pc 6. open-higgsfield → (4.4k⭐) one prompt bar, one gallery
  Read full on X, posted by @Rosasynthesiz
  @Rosasynthesiz · x.com
- 🚨 10 个 GitHub 仓库应该被视为非法的（它们正在摧毁大公司超过 500 亿美元的收入）保存它。 1. yt-dlp 下载 YouTube、X、TikTok、Instagram 和许多其他平台的任意视频。 YouTube Premium 每月收取 14 美元，只提供比这少得多的功能。它 100% 免费。仓库 → 2. Ollama 在你的笔记本电脑上直接运行 GPT-4 级别的…
  Read full on X, posted by @Encryption_007
  @Encryption_007 · x.com
- 访谈录音想变成可搜索文字，可以用开源 Whisper 本地转录。按官方文档装好工具和 FFmpeg 后运行： whisper a.mp3 --model base 把文件名换成自己的录音，首次会下载模型。需自备算力；人名、数字和专业术语要回听校对。官方：
  Read full on X, posted by @wangchuan0056
  @wangchuan0056 · x.com
Oct 141 post
- Remotion: video from code. Free for individuals and companies up to 3 people, a company license above that.
  Read full on X, posted by @inikolov_ai
  @inikolov_ai · x.com
Oct 112 posts
- You'd think an AI OS runs on the biggest model you pay for. In this Claude OS the large, slow model is Codex, kept for deep work, and the dashboard shows it at 3% of its weekly usage while Claude…
  Read full on X, posted by @itsvlady
  @itsvlady · x.com
- 剪访谈最磨人的一刻：明明记得那句话，就是找不到。 Whisper能在本机把录音转成带时间戳的文字。搜到关键词，再回听对应片段，剪辑就有了落点。人名、数字和关键表态仍要核对。AI的价值可以很朴素：少拖几遍进度条。 OpenAI官方项目 · 时间戳输出实现
  Read full on X, posted by @sun_jinwei20915
  @sun_jinwei20915 · x.com

saharmor/whisper-playground

Python

Build real time speech2text web apps using OpenAI's Whisper https://openai.com/blog/whisper/

836146

DarioFT/ComfyUI-Qwen3-ASR

Python

ComfyUI custom nodes for Qwen3-ASR (Automatic Speech Recognition) - audio-to-text transcription supporting 52 languages and dialects.

19828

QwenAudio/Fun-ASR

C

Fun-ASR speech recognition models, with native Hugging Face Transformers support for Fun-ASR-Nano and separate FunASR, vLLM and llama.cpp deployment paths.

1.6k143

ahmetoner/whisper-asr-webservice

Python

OpenAI Whisper ASR Webservice API

3.4k570

QwenAudio/SenseVoice

C

Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.

9.5k840

Softcatala/whisper-ctranslate2

Python

Whisper command line client compatible with original OpenAI client based on CTranslate2.

1.4k126

huggingface/distil-whisper

Python

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

4.1k357

seanoliver/audioflare

TypeScript

An all-in-one AI audio playground using Cloudflare AI Workers to transcribe, analyze, summarize, and translate any audio file.

48542

Carleslc/AudioToText

Jupyter Notebook

Transcribe and translate audio to text using Whisper and DeepL.

39654