From 1700765eeee7738f112bc9a087df7f8117a7a797 Mon Sep 17 00:00:00 2001 From: kalarp <145061739+kalarp@users.noreply.github.com> Date: Sat, 4 Jan 2025 17:58:02 +0100 Subject: [PATCH 1/7] Update README.md --- README.md | 96 +++++++++++++++++++++++++++++++++++-------------------- 1 file changed, 61 insertions(+), 35 deletions(-) diff --git a/README.md b/README.md index 696869c..b33a4e6 100644 --- a/README.md +++ b/README.md @@ -1,35 +1,39 @@ -# Whisper + +# Whisper [[Blog]](https://openai.com/blog/whisper) [[Paper]](https://arxiv.org/abs/2212.04356) [[Model card]](https://github.com/openai/whisper/blob/main/model-card.md) [[Colab example]](https://colab.research.google.com/github/openai/whisper/blob/master/notebooks/LibriSpeech.ipynb) -Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification. +- [Introduction](#introduction) +- [Approach](#approach) +- [Prerequisites](#prerequisites) +- [Installation](#installation) +- [Installation troubleshooting](#installation-troubleshooting) +- [Available models and languages](#available-models-and-languages) +- [Performance](#performance) +- [Command-line usage](#command-line-usage) +- [Python usage](#python-usage) +- [More examples](#more-examples) +- [License](#license) +## Introduction + +Whisper is a speech recognition model for general purpose. It is trained on a large dataset of diverse audio. Whisper is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification. + ## Approach ![Approach](https://raw.githubusercontent.com/openai/whisper/main/approach.png) -A Transformer sequence-to-sequence model is trained on various speech processing tasks, including multilingual speech recognition, speech translation, spoken language identification, and voice activity detection. These tasks are jointly represented as a sequence of tokens to be predicted by the decoder, allowing a single model to replace many stages of a traditional speech-processing pipeline. The multitask training format uses a set of special tokens that serve as task specifiers or classification targets. +A Transformer sequence-to-sequence model is trained on various speech processing tasks. The tasks include multilingual speech recognition, speech translation, spoken language identification, and voice activity detection. These tasks are jointly represented as a sequence of tokens to be predicted by the decoder. As a result, a single model replaces many steps in a traditional speech processing. The multitask training format uses a set of special tokens that serve as task specifiers or classification targets. +We used Python 3.9.9 and [PyTorch](https://pytorch.org/) 1.10.1 to train and test our models. The codebase should be compatible with Python 3.8-3.11 and recent PyTorch versions. The codebase also depends on a few Python packages, most notably [OpenAI's tiktoken](https://github.com/openai/tiktoken) for their fast tokenizer implementation. -## Setup +## Prerequisites -We used Python 3.9.9 and [PyTorch](https://pytorch.org/) 1.10.1 to train and test our models, but the codebase is expected to be compatible with Python 3.8-3.11 and recent PyTorch versions. The codebase also depends on a few Python packages, most notably [OpenAI's tiktoken](https://github.com/openai/tiktoken) for their fast tokenizer implementation. You can download and install (or update to) the latest release of Whisper with the following command: - - pip install -U openai-whisper - -Alternatively, the following command will pull and install the latest commit from this repository, along with its Python dependencies: - - pip install git+https://github.com/openai/whisper.git - -To update the package to the latest version of this repository, please run: - - pip install --upgrade --no-deps --force-reinstall git+https://github.com/openai/whisper.git - -It also requires the command-line tool [`ffmpeg`](https://ffmpeg.org/) to be installed on your system, which is available from most package managers: +* Whisper requires the command-line tool [`ffmpeg`](https://ffmpeg.org/) to be installed on your system. The command-line tool is available from most package managers: ```bash # on Ubuntu or Debian @@ -47,19 +51,41 @@ choco install ffmpeg # on Windows using Scoop (https://scoop.sh/) scoop install ffmpeg ``` +* You may need [`rust`](http://rust-lang.org) installed as well, in case [tiktoken](https://github.com/openai/tiktoken) does not provide a pre-built wheel for your platform. Follow the [Getting started page](https://www.rust-lang.org/learn/get-started) to install Rust development environment. -You may need [`rust`](http://rust-lang.org) installed as well, in case [tiktoken](https://github.com/openai/tiktoken) does not provide a pre-built wheel for your platform. If you see installation errors during the `pip install` command above, please follow the [Getting started page](https://www.rust-lang.org/learn/get-started) to install Rust development environment. Additionally, you may need to configure the `PATH` environment variable, e.g. `export PATH="$HOME/.cargo/bin:$PATH"`. If the installation fails with `No module named 'setuptools_rust'`, you need to install `setuptools_rust`, e.g. by running: +## Installation + +* You can download and install (or update to) the latest release of Whisper with the following command: + +```bash + pip install -U openai-whisper +``` + +* Alternatively, use the following command to pull and install the latest commit from this repository and its Python dependencies: + +```bash + pip install git+https://github.com/openai/whisper.git +``` + +* To update the package to the latest version of this repository, run: + +```bash + pip install --upgrade --no-deps --force-reinstall git+https://github.com/openai/whisper.git +``` +## Installation troubleshooting + +If you see installation errors during the installation of Whisper, follow these steps: +* Check if you have [`rust`](http://rust-lang.org) installed on your system. If not, follow the [Getting started page](https://www.rust-lang.org/learn/get-started) to install Rust development environment. +* Additionally, you may need to configure the `PATH` environment variable, e.g. `export PATH="$HOME/.cargo/bin:$PATH"`. +* If the installation fails with `No module named 'setuptools_rust'`, you need to install `setuptools_rust`, e.g. by running: ```bash pip install setuptools-rust ``` - ## Available models and languages -There are six model sizes, four with English-only versions, offering speed and accuracy tradeoffs. -Below are the names of the available models and their approximate memory requirements and inference speed relative to the large model. -The relative speeds below are measured by transcribing English speech on a A100, and the real-world speed may vary significantly depending on many factors including the language, the speaking speed, and the available hardware. +There are six model sizes, four with English-only versions, offering a compromise between speed and accuracy. In the table below are the names of the available models, their approximate memory requirements and inference speed relative to the large model. The relative speeds given in the table are measured by transcribing English speech on a A100. The real-world speed may vary significantly depending on many factors including the language, the speaking speed, and the available hardware. | Size | Parameters | English-only model | Multilingual model | Required VRAM | Relative speed | |:------:|:----------:|:------------------:|:------------------:|:-------------:|:--------------:| @@ -71,17 +97,19 @@ The relative speeds below are measured by transcribing English speech on a A100, | turbo | 809 M | N/A | `turbo` | ~6 GB | ~8x | The `.en` models for English-only applications tend to perform better, especially for the `tiny.en` and `base.en` models. We observed that the difference becomes less significant for the `small.en` and `medium.en` models. -Additionally, the `turbo` model is an optimized version of `large-v3` that offers faster transcription speed with a minimal degradation in accuracy. +Additionally, the `turbo` model is an optimized version of `large-v3`. It offers faster transcription speed with a minimal degradation in accuracy. -Whisper's performance varies widely depending on the language. The figure below shows a performance breakdown of `large-v3` and `large-v2` models by language, using WERs (word error rates) or CER (character error rates, shown in *Italic*) evaluated on the Common Voice 15 and Fleurs datasets. Additional WER/CER metrics corresponding to the other models and datasets can be found in Appendix D.1, D.2, and D.4 of [the paper](https://arxiv.org/abs/2212.04356), as well as the BLEU (Bilingual Evaluation Understudy) scores for translation in Appendix D.3. +## Performance + +Whisper's performance varies widely by language. The figure below shows a performance breakdown of `large-v3` and `large-v2` models by language. The performance breakdown uses WERs (Word Error Rates) or CER (Character Error Rates, shown in *Italics*) evaluated on the Common Voice 15 and Fleurs datasets. Additional WER/CER metrics corresponding to the other models and datasets can be found in: +* Appendix D.1, D.2, and D.4 of [the paper](https://arxiv.org/abs/2212.04356). +* The BLEU (Bilingual Evaluation Understudy) scores for translation in Appendix D.3. ![WER breakdown by language](https://github.com/openai/whisper/assets/266841/f4619d66-1058-4005-8f67-a9d811b77c62) - - ## Command-line usage -The following command will transcribe speech in audio files, using the `turbo` model: +The following command will transcribe speech in audio files. The command uses the `turbo` model: whisper audio.flac audio.mp3 audio.wav --model turbo @@ -89,17 +117,16 @@ The default setting (which selects the `turbo` model) works well for transcribin whisper japanese.wav --language Japanese -Adding `--task translate` will translate the speech into English: +Add `--task translate` to translate the speech into English: whisper japanese.wav --language Japanese --task translate -Run the following to view all available options: +Run the following command to view all available options: whisper --help See [tokenizer.py](https://github.com/openai/whisper/blob/main/whisper/tokenizer.py) for the list of all available languages. - ## Python usage Transcription can also be performed within Python: @@ -112,9 +139,9 @@ result = model.transcribe("audio.mp3") print(result["text"]) ``` -Internally, the `transcribe()` method reads the entire file and processes the audio with a sliding 30-second window, performing autoregressive sequence-to-sequence predictions on each window. +Internally, the `transcribe()` method reads the entire file and processes the audio with a sliding 30-second window. The method performs autoregressive sequence-to-sequence predictions on each window. -Below is an example usage of `whisper.detect_language()` and `whisper.decode()` which provide lower-level access to the model. +Below is an example usage of `whisper.detect_language()` and `whisper.decode()` which provide lower-level access to the model: ```python import whisper @@ -142,9 +169,8 @@ print(result.text) ## More examples -Please use the [🙌 Show and tell](https://github.com/openai/whisper/discussions/categories/show-and-tell) category in Discussions for sharing more example usages of Whisper and third-party extensions such as web demos, integrations with other tools, ports for different platforms, etc. - +Use the [🙌 Show and tell](https://github.com/openai/whisper/discussions/categories/show-and-tell) category in Discussions for sharing more example usages of Whisper and third-party extensions such as web demos, integrations with other tools, ports for different platforms, etc. ## License -Whisper's code and model weights are released under the MIT License. See [LICENSE](https://github.com/openai/whisper/blob/main/LICENSE) for further details. +Whisper's code and model weights are released under the MIT License. See [LICENSE](https://github.com/openai/whisper/blob/main/LICENSE) for further details. \ No newline at end of file From b43abb8b0670770538bfed1fbc04a7904e9dea23 Mon Sep 17 00:00:00 2001 From: kalarp <145061739+kalarp@users.noreply.github.com> Date: Sat, 4 Jan 2025 18:18:31 +0100 Subject: [PATCH 2/7] Update README.md --- README.md | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/README.md b/README.md index b33a4e6..e76c3c2 100644 --- a/README.md +++ b/README.md @@ -27,13 +27,13 @@ Whisper is a speech recognition model for general purpose. It is trained on a la ![Approach](https://raw.githubusercontent.com/openai/whisper/main/approach.png) -A Transformer sequence-to-sequence model is trained on various speech processing tasks. The tasks include multilingual speech recognition, speech translation, spoken language identification, and voice activity detection. These tasks are jointly represented as a sequence of tokens to be predicted by the decoder. As a result, a single model replaces many steps in a traditional speech processing. The multitask training format uses a set of special tokens that serve as task specifiers or classification targets. +A Transformer sequence-to-sequence model is trained on various speech processing tasks. The tasks include multilingual speech recognition, speech translation, spoken language identification, and voice activity detection. These tasks are jointly represented as a sequence of tokens to be predicted by the decoder. As a result, a single model replaces many steps in traditional speech processing. The multitask training format uses a set of special tokens that serve as task specifiers or classification targets. We used Python 3.9.9 and [PyTorch](https://pytorch.org/) 1.10.1 to train and test our models. The codebase should be compatible with Python 3.8-3.11 and recent PyTorch versions. The codebase also depends on a few Python packages, most notably [OpenAI's tiktoken](https://github.com/openai/tiktoken) for their fast tokenizer implementation. ## Prerequisites -* Whisper requires the command-line tool [`ffmpeg`](https://ffmpeg.org/) to be installed on your system. The command-line tool is available from most package managers: +* Whisper requires the command-line tool [`ffmpeg`](https://ffmpeg.org/) to be installed on your system. The command-line tool is available from most package managers. To install [`ffmpeg`](https://ffmpeg.org/), use one of the following commands for your operating system: ```bash # on Ubuntu or Debian @@ -51,7 +51,7 @@ choco install ffmpeg # on Windows using Scoop (https://scoop.sh/) scoop install ffmpeg ``` -* You may need [`rust`](http://rust-lang.org) installed as well, in case [tiktoken](https://github.com/openai/tiktoken) does not provide a pre-built wheel for your platform. Follow the [Getting started page](https://www.rust-lang.org/learn/get-started) to install Rust development environment. +* If [tiktoken](https://github.com/openai/tiktoken) does not provide a pre-built wheel for your platform, install [`rust`](http://rust-lang.org). Follow the [Getting started page](https://www.rust-lang.org/learn/get-started) to install the Rust development environment. ## Installation @@ -75,9 +75,9 @@ scoop install ffmpeg ## Installation troubleshooting If you see installation errors during the installation of Whisper, follow these steps: -* Check if you have [`rust`](http://rust-lang.org) installed on your system. If not, follow the [Getting started page](https://www.rust-lang.org/learn/get-started) to install Rust development environment. +* Check if you have [`rust`](http://rust-lang.org) installed on your system. If not, follow the [Getting started page](https://www.rust-lang.org/learn/get-started) to install the Rust development environment. * Additionally, you may need to configure the `PATH` environment variable, e.g. `export PATH="$HOME/.cargo/bin:$PATH"`. -* If the installation fails with `No module named 'setuptools_rust'`, you need to install `setuptools_rust`, e.g. by running: +* If the installation fails with `No module named 'setuptools_rust'`, install `setuptools_rust`. You can use the following command: ```bash pip install setuptools-rust @@ -85,7 +85,7 @@ pip install setuptools-rust ## Available models and languages -There are six model sizes, four with English-only versions, offering a compromise between speed and accuracy. In the table below are the names of the available models, their approximate memory requirements and inference speed relative to the large model. The relative speeds given in the table are measured by transcribing English speech on a A100. The real-world speed may vary significantly depending on many factors including the language, the speaking speed, and the available hardware. +There are six model sizes, four with English-only versions, offering a compromise between speed and accuracy. In the table below are the names of the available models, their approximate memory requirements and their inference speed relative to the large model. The relative speeds given in the table are measured by transcribing English speech on a A100. The real-world speed may vary significantly depending on many factors including the language, the speaking speed, and the available hardware. | Size | Parameters | English-only model | Multilingual model | Required VRAM | Relative speed | |:------:|:----------:|:------------------:|:------------------:|:-------------:|:--------------:| @@ -101,9 +101,9 @@ Additionally, the `turbo` model is an optimized version of `large-v3`. It offers ## Performance -Whisper's performance varies widely by language. The figure below shows a performance breakdown of `large-v3` and `large-v2` models by language. The performance breakdown uses WERs (Word Error Rates) or CER (Character Error Rates, shown in *Italics*) evaluated on the Common Voice 15 and Fleurs datasets. Additional WER/CER metrics corresponding to the other models and datasets can be found in: +Whisper's performance varies widely by language. The figure below shows a performance breakdown of `large-v3` and `large-v2` models by language. The performance breakdown uses Word Error Rates (WER) or Character Error Rates (CER, shown in *Italics*) evaluated on the Common Voice 15 and Fleurs datasets. Additional Word Error Rates or Character Error Rates metrics corresponding to the other models and datasets can be found in: * Appendix D.1, D.2, and D.4 of [the paper](https://arxiv.org/abs/2212.04356). -* The BLEU (Bilingual Evaluation Understudy) scores for translation in Appendix D.3. +* The Bilingual Evaluation Understudy (BLEU) scores for translation in Appendix D.3. ![WER breakdown by language](https://github.com/openai/whisper/assets/266841/f4619d66-1058-4005-8f67-a9d811b77c62) From eda5f55e80a33665e40764966a0b4c22794c6cc1 Mon Sep 17 00:00:00 2001 From: kalarp <145061739+kalarp@users.noreply.github.com> Date: Sat, 4 Jan 2025 18:21:42 +0100 Subject: [PATCH 3/7] Update README.md --- README.md | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index e76c3c2..0385ec2 100644 --- a/README.md +++ b/README.md @@ -6,6 +6,8 @@ [[Model card]](https://github.com/openai/whisper/blob/main/model-card.md) [[Colab example]](https://colab.research.google.com/github/openai/whisper/blob/master/notebooks/LibriSpeech.ipynb) +## Contents + - [Introduction](#introduction) - [Approach](#approach) - [Prerequisites](#prerequisites) @@ -76,7 +78,7 @@ scoop install ffmpeg If you see installation errors during the installation of Whisper, follow these steps: * Check if you have [`rust`](http://rust-lang.org) installed on your system. If not, follow the [Getting started page](https://www.rust-lang.org/learn/get-started) to install the Rust development environment. -* Additionally, you may need to configure the `PATH` environment variable, e.g. `export PATH="$HOME/.cargo/bin:$PATH"`. +* Additionally, you may need to configure the `PATH` environment variable. You can use the following command: `export PATH="$HOME/.cargo/bin:$PATH"`. * If the installation fails with `No module named 'setuptools_rust'`, install `setuptools_rust`. You can use the following command: ```bash @@ -169,8 +171,8 @@ print(result.text) ## More examples -Use the [🙌 Show and tell](https://github.com/openai/whisper/discussions/categories/show-and-tell) category in Discussions for sharing more example usages of Whisper and third-party extensions such as web demos, integrations with other tools, ports for different platforms, etc. +Use the [🙌 Show and tell](https://github.com/openai/whisper/discussions/categories/show-and-tell) category in Discussions for sharing more example usages of Whisper and third-party extensions such as web demos, integrations with other tools or ports for different platforms. ## License -Whisper's code and model weights are released under the MIT License. See [LICENSE](https://github.com/openai/whisper/blob/main/LICENSE) for further details. \ No newline at end of file +Whisper's code and model weights are released under the Massachusetts Institute of Technology (MIT) License. See [LICENSE](https://github.com/openai/whisper/blob/main/LICENSE) for further details. \ No newline at end of file From 8bca0f721e081a857d2251bcaba7ee218bb364c1 Mon Sep 17 00:00:00 2001 From: kalarp <145061739+kalarp@users.noreply.github.com> Date: Sat, 4 Jan 2025 18:39:05 +0100 Subject: [PATCH 4/7] Update README.md --- README.md | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 0385ec2..af2b176 100644 --- a/README.md +++ b/README.md @@ -60,25 +60,28 @@ scoop install ffmpeg * You can download and install (or update to) the latest release of Whisper with the following command: ```bash - pip install -U openai-whisper +pip install -U openai-whisper ``` * Alternatively, use the following command to pull and install the latest commit from this repository and its Python dependencies: ```bash - pip install git+https://github.com/openai/whisper.git +pip install git+https://github.com/openai/whisper.git ``` * To update the package to the latest version of this repository, run: ```bash - pip install --upgrade --no-deps --force-reinstall git+https://github.com/openai/whisper.git +pip install --upgrade --no-deps --force-reinstall git+https://github.com/openai/whisper.git ``` ## Installation troubleshooting If you see installation errors during the installation of Whisper, follow these steps: * Check if you have [`rust`](http://rust-lang.org) installed on your system. If not, follow the [Getting started page](https://www.rust-lang.org/learn/get-started) to install the Rust development environment. -* Additionally, you may need to configure the `PATH` environment variable. You can use the following command: `export PATH="$HOME/.cargo/bin:$PATH"`. +* Additionally, you may need to configure the `PATH` environment variable. You can use the following command: + ```bash +export PATH="$HOME/.cargo/bin:$PATH" +``` * If the installation fails with `No module named 'setuptools_rust'`, install `setuptools_rust`. You can use the following command: ```bash From ebcf45bb9919476cd72eabab687004e3c27a36fc Mon Sep 17 00:00:00 2001 From: kalarp <145061739+kalarp@users.noreply.github.com> Date: Sat, 4 Jan 2025 19:27:14 +0100 Subject: [PATCH 5/7] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index af2b176..f02349b 100644 --- a/README.md +++ b/README.md @@ -90,7 +90,7 @@ pip install setuptools-rust ## Available models and languages -There are six model sizes, four with English-only versions, offering a compromise between speed and accuracy. In the table below are the names of the available models, their approximate memory requirements and their inference speed relative to the large model. The relative speeds given in the table are measured by transcribing English speech on a A100. The real-world speed may vary significantly depending on many factors including the language, the speaking speed, and the available hardware. +There are six model sizes, four with English-only versions, offering a compromise between speed and accuracy. In the table below are the names of the available models, their approximate memory requirements and their inference speed relative to the large model. The relative speeds given in the table are measured by transcribing English speech on the A100 graphics processing unit (GPU). The real-world speed may vary significantly depending on many factors including the language, the speaking speed, and the available hardware. | Size | Parameters | English-only model | Multilingual model | Required VRAM | Relative speed | |:------:|:----------:|:------------------:|:------------------:|:-------------:|:--------------:| From 81f2f2d8dfca8f49380250d1628cb31e8184437b Mon Sep 17 00:00:00 2001 From: kalarp <145061739+kalarp@users.noreply.github.com> Date: Sat, 4 Jan 2025 19:51:12 +0100 Subject: [PATCH 6/7] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index f02349b..00bd926 100644 --- a/README.md +++ b/README.md @@ -23,7 +23,7 @@ ## Introduction -Whisper is a speech recognition model for general purpose. It is trained on a large dataset of diverse audio. Whisper is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification. +Whisper is a multilingual speech recognition model for general purposes, including speech translation and language identification. Whisper is trained on a large dataset of diverse audio. ## Approach From a2905a02926f489b6d5a1f899180df24b06c7a06 Mon Sep 17 00:00:00 2001 From: martab0 <35269974+martab0@users.noreply.github.com> Date: Sat, 11 Jan 2025 23:43:34 +0100 Subject: [PATCH 7/7] Improve structure --- README.md | 45 +++++++++++++++++++++++++++------------------ 1 file changed, 27 insertions(+), 18 deletions(-) diff --git a/README.md b/README.md index 00bd926..8d8774e 100644 --- a/README.md +++ b/README.md @@ -8,11 +8,11 @@ ## Contents -- [Introduction](#introduction) -- [Approach](#approach) -- [Prerequisites](#prerequisites) -- [Installation](#installation) -- [Installation troubleshooting](#installation-troubleshooting) +- [What is Whisper](#what-is-whisper) +- [Setup](#setup) + - [Prerequsites](#prerequisites) + - [Installation](#installation) + - [Installation troubleshooting](#installation-troubleshooting) - [Available models and languages](#available-models-and-languages) - [Performance](#performance) - [Command-line usage](#command-line-usage) @@ -20,42 +20,50 @@ - [More examples](#more-examples) - [License](#license) - -## Introduction +## What is Whisper Whisper is a multilingual speech recognition model for general purposes, including speech translation and language identification. Whisper is trained on a large dataset of diverse audio. -## Approach - ![Approach](https://raw.githubusercontent.com/openai/whisper/main/approach.png) A Transformer sequence-to-sequence model is trained on various speech processing tasks. The tasks include multilingual speech recognition, speech translation, spoken language identification, and voice activity detection. These tasks are jointly represented as a sequence of tokens to be predicted by the decoder. As a result, a single model replaces many steps in traditional speech processing. The multitask training format uses a set of special tokens that serve as task specifiers or classification targets. We used Python 3.9.9 and [PyTorch](https://pytorch.org/) 1.10.1 to train and test our models. The codebase should be compatible with Python 3.8-3.11 and recent PyTorch versions. The codebase also depends on a few Python packages, most notably [OpenAI's tiktoken](https://github.com/openai/tiktoken) for their fast tokenizer implementation. -## Prerequisites +## Setup + +### Prerequisites * Whisper requires the command-line tool [`ffmpeg`](https://ffmpeg.org/) to be installed on your system. The command-line tool is available from most package managers. To install [`ffmpeg`](https://ffmpeg.org/), use one of the following commands for your operating system: +**on Ubuntu or Debian** ```bash -# on Ubuntu or Debian sudo apt update && sudo apt install ffmpeg +``` -# on Arch Linux +**on Arch Linux** +```bash sudo pacman -S ffmpeg +``` -# on MacOS using Homebrew (https://brew.sh/) +**on MacOS using Homebrew (https://brew.sh/)** +```bash brew install ffmpeg +``` -# on Windows using Chocolatey (https://chocolatey.org/) +**on Windows using Chocolatey (https://chocolatey.org/)** +```bash choco install ffmpeg +``` -# on Windows using Scoop (https://scoop.sh/) +**on Windows using Scoop (https://scoop.sh/)** +```bash scoop install ffmpeg ``` + * If [tiktoken](https://github.com/openai/tiktoken) does not provide a pre-built wheel for your platform, install [`rust`](http://rust-lang.org). Follow the [Getting started page](https://www.rust-lang.org/learn/get-started) to install the Rust development environment. -## Installation +### Installation * You can download and install (or update to) the latest release of Whisper with the following command: @@ -74,7 +82,8 @@ pip install git+https://github.com/openai/whisper.git ```bash pip install --upgrade --no-deps --force-reinstall git+https://github.com/openai/whisper.git ``` -## Installation troubleshooting + +### Installation troubleshooting If you see installation errors during the installation of Whisper, follow these steps: * Check if you have [`rust`](http://rust-lang.org) installed on your system. If not, follow the [Getting started page](https://www.rust-lang.org/learn/get-started) to install the Rust development environment. @@ -178,4 +187,4 @@ Use the [🙌 Show and tell](https://github.com/openai/whisper/discussions/categ ## License -Whisper's code and model weights are released under the Massachusetts Institute of Technology (MIT) License. See [LICENSE](https://github.com/openai/whisper/blob/main/LICENSE) for further details. \ No newline at end of file +Whisper's code and model weights are released under the Massachusetts Institute of Technology (MIT) License. See [LICENSE](https://github.com/openai/whisper/blob/main/LICENSE) for further details.