Official documentation
openai/whisper: README (raw text)
OpenAI, GitHub (openai/whisper), 2026
Read the originalRead on October 17, 2026
- What it is
- The README of OpenAI's open-source Whisper repository, in its raw markdown form. It gives the installation commands, the ffmpeg requirement, the model table with parameters, memory and relative speed, and the command-line examples.
- How much weight it carries
- The official project documentation, maintained by the team that trained the models. Relative speeds are measured on an A100 GPU and the README warns that real speed depends on language, audio and hardware.
Facts taken from this source
- OpenAI's README for Whisper says that its code and model weights are released under the MIT License, a permissive license that lets anyone use them, including for free.
“Whisper's code and model weights are released under the MIT License.” (License section)
- OpenAI's Whisper README says the model's performance varies widely depending on the language, and it publishes a breakdown by language for its two largest models.
“Whisper's performance varies widely depending on the language.” (Available models and languages)
- The base Whisper model runs at about 7 times the relative speed of the large model.
“| base | 74 M | `base.en` | `base` | ~1 GB | ~7x |” (Available models and languages table)
- The base Whisper model needs about 1 GB of video memory.
“| base | 74 M | `base.en` | `base` | ~1 GB | ~7x |” (Available models and languages table)
- OpenAI's README says its English-only .en models tend to perform better for English applications, especially the tiny and base sizes.
“The `.en` models for English-only applications tend to perform better, especially for the `tiny.en` and `base.en` models.” (Available models and languages)
- The medium Whisper model runs at about 2 times the relative speed of the large model.
“| medium | 769 M | `medium.en` | `medium` | ~5 GB | ~2x |” (Available models and languages table)
- The small Whisper model runs at about 4 times the relative speed of the large model.
“| small | 244 M | `small.en` | `small` | ~2 GB | ~4x |” (Available models and languages table)
- The turbo Whisper model has 809 million parameters.
“| turbo | 809 M | N/A | `turbo` | ~6 GB | ~8x |” (Available models and languages table)
- The turbo Whisper model is not trained for translation tasks, so translating non-English speech into English needs a multilingual model such as medium or large.
“However, **the `turbo` model is not trained for translation tasks**.” (Command-line usage)
- The turbo Whisper model runs at about 8 times the relative speed of the large model.
“| turbo | 809 M | N/A | `turbo` | ~6 GB | ~8x |” (Available models and languages table)
- The turbo Whisper model needs about 6 GB of video memory, less than the 10 GB the large model needs.
“| turbo | 809 M | N/A | `turbo` | ~6 GB | ~8x |” (Available models and languages table)
- The Whisper README gives a pip command with --force-reinstall to update the package to the latest version of its repository.
“pip install --upgrade --no-deps --force-reinstall git+https://github.com/openai/whisper.git” (Setup)
- The openai-whisper README introduces command-line use by saying that the following command will transcribe speech in audio files.
“The following command will transcribe speech in audio files” (Command-line usage section)
- The Whisper README says its default setting selects the turbo model, and that the default works well for transcribing English.
“The default setting (which selects the `turbo` model) works well for transcribing English” (Translation section of the README)
- The Whisper README says that the turbo model returns the original language when the translate task is set, and recommends the medium or large model for the best translation results.
“Use `medium` or `large` for the best translation results.” (Translation section of the README, after the translate example)
- OpenAI released Whisper's code and model weights under the MIT License.
“Whisper's code and model weights are released under the MIT License.” (License section)
- The Whisper README says the package also requires the ffmpeg command-line tool to be installed on your system.
“to be installed on your system, which is available from most package managers” (Setup section of the README)
- The Whisper README's example for translating Japanese speech into English uses the medium model, the language flag set to Japanese and the translate task.
“whisper japanese.wav --model medium --language Japanese --task translate” (Usage section, translation example)
- The Whisper README says the turbo model is not trained for translation tasks, and that translating non-English speech into English needs one of the multilingual models: tiny, base, small, medium or large.
“the `turbo` model is not trained for translation tasks” (Usage section, after the default command)
- The Whisper README says the turbo model returns the original language even when the translate task is specified.
“The `turbo` model will return the original language even if `--task translate` is specified.” (Usage section, translation note)
Pages that rest on this source
- Is there a free speech to text AI?Question
- Whisper Supported Languages and Accuracy by LanguageGuide
- How do you translate Japanese audio to English?Question
- Which Whisper model should I use?Question
- Video to Text: Transcribe Videos and YouTubeGuide
- How to Run Whisper Locally on Your Own ComputerGuide
- Is Whisper AI Safe? Privacy and Security ExplainedGuide
- Transcribe Audio With Whisper, ChatGPT or GeminiGuide
- What is the best GPU for Whisper?Question
- How to Transcribe Audio to TextGuide
- Spanish Speech to Text and Talk to TextGuide
- How do you talk to text in Spanish and get English?Question
- How do you transcribe a long audio file, such as one over 30 minutes?Question
- Can Whisper run without a GPU?Question
- How do you install Whisper AI?Question
- How do you use Whisper to transcribe audio?Question
- Why is Whisper not using my GPU?Question
- Do you need an OpenAI API key to use Whisper offline?Question
- Can Whisper translate audio?Question
- How do you run Whisper in Google Colab?Question
- How do you translate a video into English subtitles?Question
- How to Translate Audio and Video to English TextGuide
- History of Speech Recognition: From Audrey to WhisperGuide
- Can Whisper AI run offline?Question