extern/whisper.cpp
1
0
Fork 1
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-04-23 10:51:22 +02:00
Code Issues Packages Projects Releases Wiki Activity

rename : ggerganov -> ggml-org (#3005)

Browse Source
This commit is contained in:
Georgi Gerganov 2025-04-04 16:11:52 +03:00 committed by GitHub
parent 0b17d4507e
commit 2b6d0d2200
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
15 changed files with 61 additions and 63 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

63
README.md
View File

@ -2,12 +2,12 @@
![whisper.cpp](https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg) ![whisper.cpp](https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg)
[![Actions Status](https://github.com/ggerganov/whisper.cpp/workflows/CI/badge.svg)](https://github.com/ggerganov/whisper.cpp/actions) [![Actions Status](https://github.com/ggml-org/whisper.cpp/workflows/CI/badge.svg)](https://github.com/ggml-org/whisper.cpp/actions)
[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](https://opensource.org/licenses/MIT) [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](https://opensource.org/licenses/MIT)
[![Conan Center](https://shields.io/conan/v/whisper-cpp)](https://conan.io/center/whisper-cpp) [![Conan Center](https://shields.io/conan/v/whisper-cpp)](https://conan.io/center/whisper-cpp)
[![npm](https://img.shields.io/npm/v/whisper.cpp.svg)](https://www.npmjs.com/package/whisper.cpp/) [![npm](https://img.shields.io/npm/v/whisper.cpp.svg)](https://www.npmjs.com/package/whisper.cpp/)
Stable: [v1.7.5](https://github.com/ggerganov/whisper.cpp/releases/tag/v1.7.5) / [Roadmap](https://github.com/users/ggerganov/projects/16/) Stable: [v1.7.5](https://github.com/ggml-org/whisper.cpp/releases/tag/v1.7.5) / [Roadmap](https://github.com/orgs/ggml-org/projects/4/)
High-performance inference of [OpenAI's Whisper](https://github.com/openai/whisper) automatic speech recognition (ASR) model: High-performance inference of [OpenAI's Whisper](https://github.com/openai/whisper) automatic speech recognition (ASR) model:
@ -23,7 +23,7 @@ High-performance inference of [OpenAI's Whisper](https://github.com/openai/whisp
- [Efficient GPU support for NVIDIA](#nvidia-gpu-support) - [Efficient GPU support for NVIDIA](#nvidia-gpu-support)
- [OpenVINO Support](#openvino-support) - [OpenVINO Support](#openvino-support)
- [Ascend NPU Support](#ascend-npu-support) - [Ascend NPU Support](#ascend-npu-support)
- [C-style API](https://github.com/ggerganov/whisper.cpp/blob/master/include/whisper.h) - [C-style API](https://github.com/ggml-org/whisper.cpp/blob/master/include/whisper.h)
Supported platforms: Supported platforms:
@ -31,14 +31,14 @@ Supported platforms:
- [x] [iOS](examples/whisper.objc) - [x] [iOS](examples/whisper.objc)
- [x] [Android](examples/whisper.android) - [x] [Android](examples/whisper.android)
- [x] [Java](bindings/java/README.md) - [x] [Java](bindings/java/README.md)
- [x] Linux / [FreeBSD](https://github.com/ggerganov/whisper.cpp/issues/56#issuecomment-1350920264) - [x] Linux / [FreeBSD](https://github.com/ggml-org/whisper.cpp/issues/56#issuecomment-1350920264)
- [x] [WebAssembly](examples/whisper.wasm) - [x] [WebAssembly](examples/whisper.wasm)
- [x] Windows ([MSVC](https://github.com/ggerganov/whisper.cpp/blob/master/.github/workflows/build.yml#L117-L144) and [MinGW](https://github.com/ggerganov/whisper.cpp/issues/168)] - [x] Windows ([MSVC](https://github.com/ggml-org/whisper.cpp/blob/master/.github/workflows/build.yml#L117-L144) and [MinGW](https://github.com/ggml-org/whisper.cpp/issues/168)]
- [x] [Raspberry Pi](https://github.com/ggerganov/whisper.cpp/discussions/166) - [x] [Raspberry Pi](https://github.com/ggml-org/whisper.cpp/discussions/166)
- [x] [Docker](https://github.com/ggerganov/whisper.cpp/pkgs/container/whisper.cpp) - [x] [Docker](https://github.com/ggml-org/whisper.cpp/pkgs/container/whisper.cpp)
The entire high-level implementation of the model is contained in [whisper.h](include/whisper.h) and [whisper.cpp](src/whisper.cpp). The entire high-level implementation of the model is contained in [whisper.h](include/whisper.h) and [whisper.cpp](src/whisper.cpp).
The rest of the code is part of the [`ggml`](https://github.com/ggerganov/ggml) machine learning library. The rest of the code is part of the [`ggml`](https://github.com/ggml-org/ggml) machine learning library.
Having such a lightweight implementation of the model allows to easily integrate it in different platforms and applications. Having such a lightweight implementation of the model allows to easily integrate it in different platforms and applications.
As an example, here is a video of running the model on an iPhone 13 device - fully offline, on-device: [whisper.objc](examples/whisper.objc) As an example, here is a video of running the model on an iPhone 13 device - fully offline, on-device: [whisper.objc](examples/whisper.objc)
@ -51,14 +51,14 @@ https://user-images.githubusercontent.com/1991296/204038393-2f846eae-c255-4099-a
On Apple Silicon, the inference runs fully on the GPU via Metal: On Apple Silicon, the inference runs fully on the GPU via Metal:
https://github.com/ggerganov/whisper.cpp/assets/1991296/c82e8f86-60dc-49f2-b048-d2fdbd6b5225 https://github.com/ggml-org/whisper.cpp/assets/1991296/c82e8f86-60dc-49f2-b048-d2fdbd6b5225
## Quick start ## Quick start
First clone the repository: First clone the repository:
```bash ```bash
git clone https://github.com/ggerganov/whisper.cpp.git git clone https://github.com/ggml-org/whisper.cpp.git
``` ```
Navigate into the directory: Navigate into the directory:
@ -222,7 +222,7 @@ speed-up - more than x3 faster compared with CPU-only execution. Here are the in
The first run on a device is slow, since the ANE service compiles the Core ML model to some device-specific format. The first run on a device is slow, since the ANE service compiles the Core ML model to some device-specific format.
Next runs are faster. Next runs are faster.
For more information about the Core ML implementation please refer to PR [#566](https://github.com/ggerganov/whisper.cpp/pull/566). For more information about the Core ML implementation please refer to PR [#566](https://github.com/ggml-org/whisper.cpp/pull/566).
## OpenVINO support ## OpenVINO support
@ -307,7 +307,7 @@ This can result in significant speedup in encoder performance. Here are the inst
The first time run on an OpenVINO device is slow, since the OpenVINO framework will compile the IR (Intermediate Representation) model to a device-specific 'blob'. This device-specific blob will get The first time run on an OpenVINO device is slow, since the OpenVINO framework will compile the IR (Intermediate Representation) model to a device-specific 'blob'. This device-specific blob will get
cached for the next run. cached for the next run.
For more information about the OpenVINO implementation please refer to PR [#1037](https://github.com/ggerganov/whisper.cpp/pull/1037). For more information about the OpenVINO implementation please refer to PR [#1037](https://github.com/ggml-org/whisper.cpp/pull/1037).
## NVIDIA GPU support ## NVIDIA GPU support
@ -385,8 +385,8 @@ Run the inference examples as usual, for example:
We have two Docker images available for this project: We have two Docker images available for this project:
1. `ghcr.io/ggerganov/whisper.cpp:main`: This image includes the main executable file as well as `curl` and `ffmpeg`. (platforms: `linux/amd64`, `linux/arm64`) 1. `ghcr.io/ggml-org/whisper.cpp:main`: This image includes the main executable file as well as `curl` and `ffmpeg`. (platforms: `linux/amd64`, `linux/arm64`)
2. `ghcr.io/ggerganov/whisper.cpp:main-cuda`: Same as `main` but compiled with CUDA support. (platforms: `linux/amd64`) 2. `ghcr.io/ggml-org/whisper.cpp:main-cuda`: Same as `main` but compiled with CUDA support. (platforms: `linux/amd64`)
### Usage ### Usage
@ -424,7 +424,7 @@ For detailed instructions on how to use Conan, please refer to the [Conan docume
This is a naive example of performing real-time inference on audio from your microphone. This is a naive example of performing real-time inference on audio from your microphone.
The [stream](examples/stream) tool samples the audio every half a second and runs the transcription continuously. The [stream](examples/stream) tool samples the audio every half a second and runs the transcription continuously.
More info is available in [issue #10](https://github.com/ggerganov/whisper.cpp/issues/10). More info is available in [issue #10](https://github.com/ggml-org/whisper.cpp/issues/10).
You will need to have [sdl2](https://wiki.libsdl.org/SDL2/Installation) installed for it to work properly. You will need to have [sdl2](https://wiki.libsdl.org/SDL2/Installation) installed for it to work properly.
```bash ```bash
@ -513,7 +513,7 @@ main: processing './samples/jfk.wav' (176000 samples, 11.0 sec), 4 threads, 1 pr
## Speaker segmentation via tinydiarize (experimental) ## Speaker segmentation via tinydiarize (experimental)
More information about this approach is available here: https://github.com/ggerganov/whisper.cpp/pull/1058 More information about this approach is available here: https://github.com/ggml-org/whisper.cpp/pull/1058
Sample usage: Sample usage:
@ -577,7 +577,7 @@ https://user-images.githubusercontent.com/1991296/199337538-b7b0c7a3-2753-4a88-a
## Video comparison of different models ## Video comparison of different models
Use the [scripts/bench-wts.sh](https://github.com/ggerganov/whisper.cpp/blob/master/scripts/bench-wts.sh) script to generate a video in the following format: Use the [scripts/bench-wts.sh](https://github.com/ggml-org/whisper.cpp/blob/master/scripts/bench-wts.sh) script to generate a video in the following format:
```bash ```bash
./scripts/bench-wts.sh samples/jfk.wav ./scripts/bench-wts.sh samples/jfk.wav
@ -594,7 +594,7 @@ In order to have an objective comparison of the performance of the inference acr
use the [whisper-bench](examples/bench) tool. The tool simply runs the Encoder part of the model and prints how much time it use the [whisper-bench](examples/bench) tool. The tool simply runs the Encoder part of the model and prints how much time it
took to execute it. The results are summarized in the following Github issue: took to execute it. The results are summarized in the following Github issue:
[Benchmark results](https://github.com/ggerganov/whisper.cpp/issues/89) [Benchmark results](https://github.com/ggml-org/whisper.cpp/issues/89)
Additionally a script to run whisper.cpp with different models and audio files is provided [bench.py](scripts/bench.py). Additionally a script to run whisper.cpp with different models and audio files is provided [bench.py](scripts/bench.py).
@ -621,25 +621,24 @@ You can download the converted models using the [models/download-ggml-model.sh](
or manually from here: or manually from here:
- https://huggingface.co/ggerganov/whisper.cpp - https://huggingface.co/ggerganov/whisper.cpp
- https://ggml.ggerganov.com
For more details, see the conversion script [models/convert-pt-to-ggml.py](models/convert-pt-to-ggml.py) or [models/README.md](models/README.md). For more details, see the conversion script [models/convert-pt-to-ggml.py](models/convert-pt-to-ggml.py) or [models/README.md](models/README.md).
## [Bindings](https://github.com/ggerganov/whisper.cpp/discussions/categories/bindings) ## [Bindings](https://github.com/ggml-org/whisper.cpp/discussions/categories/bindings)
- [x] Rust: [tazz4843/whisper-rs](https://github.com/tazz4843/whisper-rs) | [#310](https://github.com/ggerganov/whisper.cpp/discussions/310) - [x] Rust: [tazz4843/whisper-rs](https://github.com/tazz4843/whisper-rs) | [#310](https://github.com/ggml-org/whisper.cpp/discussions/310)
- [x] JavaScript: [bindings/javascript](bindings/javascript) | [#309](https://github.com/ggerganov/whisper.cpp/discussions/309) - [x] JavaScript: [bindings/javascript](bindings/javascript) | [#309](https://github.com/ggml-org/whisper.cpp/discussions/309)
- React Native (iOS / Android): [whisper.rn](https://github.com/mybigday/whisper.rn) - React Native (iOS / Android): [whisper.rn](https://github.com/mybigday/whisper.rn)
- [x] Go: [bindings/go](bindings/go) | [#312](https://github.com/ggerganov/whisper.cpp/discussions/312) - [x] Go: [bindings/go](bindings/go) | [#312](https://github.com/ggml-org/whisper.cpp/discussions/312)
- [x] Java: - [x] Java:
- [GiviMAD/whisper-jni](https://github.com/GiviMAD/whisper-jni) - [GiviMAD/whisper-jni](https://github.com/GiviMAD/whisper-jni)
- [x] Ruby: [bindings/ruby](bindings/ruby) | [#507](https://github.com/ggerganov/whisper.cpp/discussions/507) - [x] Ruby: [bindings/ruby](bindings/ruby) | [#507](https://github.com/ggml-org/whisper.cpp/discussions/507)
- [x] Objective-C / Swift: [ggerganov/whisper.spm](https://github.com/ggerganov/whisper.spm) | [#313](https://github.com/ggerganov/whisper.cpp/discussions/313) - [x] Objective-C / Swift: [ggml-org/whisper.spm](https://github.com/ggml-org/whisper.spm) | [#313](https://github.com/ggml-org/whisper.cpp/discussions/313)
- [exPHAT/SwiftWhisper](https://github.com/exPHAT/SwiftWhisper) - [exPHAT/SwiftWhisper](https://github.com/exPHAT/SwiftWhisper)
- [x] .NET: | [#422](https://github.com/ggerganov/whisper.cpp/discussions/422) - [x] .NET: | [#422](https://github.com/ggml-org/whisper.cpp/discussions/422)
- [sandrohanea/whisper.net](https://github.com/sandrohanea/whisper.net) - [sandrohanea/whisper.net](https://github.com/sandrohanea/whisper.net)
- [NickDarvey/whisper](https://github.com/NickDarvey/whisper) - [NickDarvey/whisper](https://github.com/NickDarvey/whisper)
- [x] Python: | [#9](https://github.com/ggerganov/whisper.cpp/issues/9) - [x] Python: | [#9](https://github.com/ggml-org/whisper.cpp/issues/9)
- [stlukey/whispercpp.py](https://github.com/stlukey/whispercpp.py) (Cython) - [stlukey/whispercpp.py](https://github.com/stlukey/whispercpp.py) (Cython)
- [AIWintermuteAI/whispercpp](https://github.com/AIWintermuteAI/whispercpp) (Updated fork of aarnphm/whispercpp) - [AIWintermuteAI/whispercpp](https://github.com/AIWintermuteAI/whispercpp) (Updated fork of aarnphm/whispercpp)
- [aarnphm/whispercpp](https://github.com/aarnphm/whispercpp) (Pybind11) - [aarnphm/whispercpp](https://github.com/aarnphm/whispercpp) (Pybind11)
@ -667,7 +666,7 @@ let package = Package(
]), ]),
.binaryTarget( .binaryTarget(
name: "WhisperFramework", name: "WhisperFramework",
url: "https://github.com/ggerganov/whisper.cpp/releases/download/v1.7.5/whisper-v1.7.5-xcframework.zip", url: "https://github.com/ggml-org/whisper.cpp/releases/download/v1.7.5/whisper-v1.7.5-xcframework.zip",
checksum: "c7faeb328620d6012e130f3d705c51a6ea6c995605f2df50f6e1ad68c59c6c4a" checksum: "c7faeb328620d6012e130f3d705c51a6ea6c995605f2df50f6e1ad68c59c6c4a"
) )
] ]
@ -692,13 +691,13 @@ Some of the examples are even ported to run in the browser using WebAssembly. Ch
| [whisper.android](examples/whisper.android) | | Android mobile application using whisper.cpp | | [whisper.android](examples/whisper.android) | | Android mobile application using whisper.cpp |
| [whisper.nvim](examples/whisper.nvim) | | Speech-to-text plugin for Neovim | | [whisper.nvim](examples/whisper.nvim) | | Speech-to-text plugin for Neovim |
| [generate-karaoke.sh](examples/generate-karaoke.sh) | | Helper script to easily [generate a karaoke video](https://youtu.be/uj7hVta4blM) of raw audio capture | | [generate-karaoke.sh](examples/generate-karaoke.sh) | | Helper script to easily [generate a karaoke video](https://youtu.be/uj7hVta4blM) of raw audio capture |
| [livestream.sh](examples/livestream.sh) | | [Livestream audio transcription](https://github.com/ggerganov/whisper.cpp/issues/185) | | [livestream.sh](examples/livestream.sh) | | [Livestream audio transcription](https://github.com/ggml-org/whisper.cpp/issues/185) |
| [yt-wsp.sh](examples/yt-wsp.sh) | | Download + transcribe and/or translate any VOD [(original)](https://gist.github.com/DaniruKun/96f763ec1a037cc92fe1a059b643b818) | | [yt-wsp.sh](examples/yt-wsp.sh) | | Download + transcribe and/or translate any VOD [(original)](https://gist.github.com/DaniruKun/96f763ec1a037cc92fe1a059b643b818) |
| [wchess](examples/wchess) | [wchess.wasm](examples/wchess) | Voice-controlled chess | | [wchess](examples/wchess) | [wchess.wasm](examples/wchess) | Voice-controlled chess |
## [Discussions](https://github.com/ggerganov/whisper.cpp/discussions) ## [Discussions](https://github.com/ggml-org/whisper.cpp/discussions)
If you have any kind of feedback about this project feel free to use the Discussions section and open a new topic. If you have any kind of feedback about this project feel free to use the Discussions section and open a new topic.
You can use the [Show and tell](https://github.com/ggerganov/whisper.cpp/discussions/categories/show-and-tell) category You can use the [Show and tell](https://github.com/ggml-org/whisper.cpp/discussions/categories/show-and-tell) category
to share your own projects that use `whisper.cpp`. If you have a question, make sure to check the to share your own projects that use `whisper.cpp`. If you have a question, make sure to check the
[Frequently asked questions (#126)](https://github.com/ggerganov/whisper.cpp/discussions/126) discussion. [Frequently asked questions (#126)](https://github.com/ggml-org/whisper.cpp/discussions/126) discussion.

4
bindings/go/README.md
View File

@ -51,7 +51,7 @@ func main() {
In order to build, you need to have the Go compiler installed. You can get it from [here](https://golang.org/dl/). Run the tests with: In order to build, you need to have the Go compiler installed. You can get it from [here](https://golang.org/dl/). Run the tests with:
```bash ```bash
git clone https://github.com/ggerganov/whisper.cpp.git git clone https://github.com/ggml-org/whisper.cpp.git
cd whisper.cpp/bindings/go cd whisper.cpp/bindings/go
make test make test
``` ```
@ -98,7 +98,7 @@ The API Documentation:
Getting help: Getting help:
* Follow the discussion for the go bindings [here](https://github.com/ggerganov/whisper.cpp/discussions/312) * Follow the discussion for the go bindings [here](https://github.com/ggml-org/whisper.cpp/discussions/312)
## License ## License

2
bindings/go/doc.go
View File

@ -1,5 +1,5 @@
/* /*
github.com/ggerganov/whisper.cpp/bindings/go github.com/ggml-org/whisper.cpp/bindings/go
provides a speech-to-text service bindings for the Go programming language. provides a speech-to-text service bindings for the Go programming language.
*/ */
package whisper package whisper

2
bindings/java/README.md
View File

@ -52,7 +52,7 @@ public class Example {
In order to build, you need to have the JDK 8 or higher installed. Run the tests with: In order to build, you need to have the JDK 8 or higher installed. Run the tests with:
```bash ```bash
git clone https://github.com/ggerganov/whisper.cpp.git git clone https://github.com/ggml-org/whisper.cpp.git
cd whisper.cpp/bindings/java cd whisper.cpp/bindings/java
./gradlew build ./gradlew build

6
bindings/ruby/README.md
View File

@ -228,7 +228,7 @@ The second argument `samples` may be an array, an object with `length` and `each
Development Development
----------- -----------
% git clone https://github.com/ggerganov/whisper.cpp.git % git clone https://github.com/ggml-org/whisper.cpp.git
% cd whisper.cpp/bindings/ruby % cd whisper.cpp/bindings/ruby
% rake test % rake test
@ -241,5 +241,5 @@ License
The same to [whisper.cpp][]. The same to [whisper.cpp][].
[whisper.cpp]: https://github.com/ggerganov/whisper.cpp [whisper.cpp]: https://github.com/ggml-org/whisper.cpp
[models]: https://github.com/ggerganov/whisper.cpp/tree/master/models [models]: https://github.com/ggml-org/whisper.cpp/tree/master/models

4
examples/bench/README.md
View File

@ -4,7 +4,7 @@ A very basic tool for benchmarking the inference performance on your device. The
the transformer on some random audio data and records the execution time. This way we can have an objective comparison the transformer on some random audio data and records the execution time. This way we can have an objective comparison
of the performance of the model for various setups. of the performance of the model for various setups.
Benchmark results are tracked in the following Github issue: https://github.com/ggerganov/whisper.cpp/issues/89 Benchmark results are tracked in the following Github issue: https://github.com/ggml-org/whisper.cpp/issues/89
```bash ```bash
# run the bench too on the small.en model using 4 threads # run the bench too on the small.en model using 4 threads
@ -40,7 +40,7 @@ system_info: n_threads = 4 | AVX2 = 0 | AVX512 = 0 | NEON = 1 | FP16_VA = 1 | WA
If you wish, you can submit these results here: If you wish, you can submit these results here:
https://github.com/ggerganov/whisper.cpp/issues/89 https://github.com/ggml-org/whisper.cpp/issues/89
Please include the following information: Please include the following information:

2
examples/command/command.cpp
View File

@ -3,7 +3,7 @@
// Speak short text commands to the microphone. // Speak short text commands to the microphone.
// This program will detect your voice command and convert them to text. // This program will detect your voice command and convert them to text.
// //
// ref: https://github.com/ggerganov/whisper.cpp/issues/171 // ref: https://github.com/ggml-org/whisper.cpp/issues/171
// //
#include "common-sdl.h" #include "common-sdl.h"

2
examples/livestream.sh
View File

@ -2,7 +2,7 @@
# #
# Transcribe audio livestream by feeding ffmpeg output to whisper.cpp at regular intervals # Transcribe audio livestream by feeding ffmpeg output to whisper.cpp at regular intervals
# Idea by @semiformal-net # Idea by @semiformal-net
# ref: https://github.com/ggerganov/whisper.cpp/issues/185 # ref: https://github.com/ggml-org/whisper.cpp/issues/185
# #
set -eo pipefail set -eo pipefail

2
examples/twitch.sh
View File

@ -2,7 +2,7 @@
# #
# Transcribe twitch.tv livestream by feeding audio input to whisper.cpp at regular intervals # Transcribe twitch.tv livestream by feeding audio input to whisper.cpp at regular intervals
# Thanks to @keyehzy # Thanks to @keyehzy
# ref: https://github.com/ggerganov/whisper.cpp/issues/209 # ref: https://github.com/ggml-org/whisper.cpp/issues/209
# #
# The script currently depends on the third-party tool "streamlink" # The script currently depends on the third-party tool "streamlink"
# On Mac OS, you can install it via "brew install streamlink" # On Mac OS, you can install it via "brew install streamlink"

4
examples/whisper.nvim/whisper.nvim
View File

@ -5,7 +5,7 @@
# This simple script is called by Neovim to capture audio from the microphone and transcribe it with Whisper. # This simple script is called by Neovim to capture audio from the microphone and transcribe it with Whisper.
# In order for this to work, you need to clone the whisper.cpp repo and build the 'stream' tool # In order for this to work, you need to clone the whisper.cpp repo and build the 'stream' tool
# #
# git clone https://github.com/ggerganov/whisper.cpp # git clone https://github.com/ggml-org/whisper.cpp
# cd whisper.cpp # cd whisper.cpp
# make stream # make stream
# #
@ -31,7 +31,7 @@
model="base.en" model="base.en"
# export the path to the whisper.cpp repo in the WHISPER_CPP_HOME env variable # export the path to the whisper.cpp repo in the WHISPER_CPP_HOME env variable
# https://github.com/ggerganov/whisper.cpp # https://github.com/ggml-org/whisper.cpp
cd "${WHISPER_CPP_HOME}" cd "${WHISPER_CPP_HOME}"
if [ ! -f ./stream ] ; then if [ ! -f ./stream ] ; then

2
examples/whisper.wasm/README.md
View File

@ -30,7 +30,7 @@ Link: https://ggerganov.github.io/whisper.cpp/
```bash (v3.1.2) ```bash (v3.1.2)
# build using Emscripten # build using Emscripten
git clone https://github.com/ggerganov/whisper.cpp git clone https://github.com/ggml-org/whisper.cpp
cd whisper.cpp cd whisper.cpp
mkdir build-em && cd build-em mkdir build-em && cd build-em
emcmake cmake .. emcmake cmake ..

10
examples/yt-wsp.sh
View File

@ -25,12 +25,12 @@
# SOFTWARE. # SOFTWARE.
# Small shell script to more easily automatically download and transcribe live stream VODs. # Small shell script to more easily automatically download and transcribe live stream VODs.
# This uses YT-DLP, ffmpeg and the CPP version of Whisper: https://github.com/ggerganov/whisper.cpp # This uses YT-DLP, ffmpeg and the CPP version of Whisper: https://github.com/ggml-org/whisper.cpp
# Use `./examples/yt-wsp.sh help` to print help info. # Use `./examples/yt-wsp.sh help` to print help info.
# #
# Sample usage: # Sample usage:
# #
# git clone https://github.com/ggerganov/whisper.cpp # git clone https://github.com/ggml-org/whisper.cpp
# cd whisper.cpp # cd whisper.cpp
# make # make
# ./examples/yt-wsp.sh https://www.youtube.com/watch?v=1234567890 # ./examples/yt-wsp.sh https://www.youtube.com/watch?v=1234567890
@ -44,7 +44,7 @@ SCRIPT_DIR="${SCRIPT_PATH%/*}"
################################################################################ ################################################################################
# Documentation on downloading models can be found in the whisper.cpp repo: # Documentation on downloading models can be found in the whisper.cpp repo:
# https://github.com/ggerganov/whisper.cpp/#usage # https://github.com/ggml-org/whisper.cpp/#usage
# #
# note: unless a multilingual model is specified, WHISPER_LANG will be ignored # note: unless a multilingual model is specified, WHISPER_LANG will be ignored
# and the video will be transcribed as if the audio were in the English language # and the video will be transcribed as if the audio were in the English language
@ -103,10 +103,10 @@ check_requirements() {
fi; fi;
if ! command -v "${WHISPER_EXECUTABLE}" &>/dev/null; then if ! command -v "${WHISPER_EXECUTABLE}" &>/dev/null; then
echo "The C++ implementation of Whisper is required: https://github.com/ggerganov/whisper.cpp" echo "The C++ implementation of Whisper is required: https://github.com/ggml-org/whisper.cpp"
echo "Sample usage:"; echo "Sample usage:";
echo ""; echo "";
echo " git clone https://github.com/ggerganov/whisper.cpp"; echo " git clone https://github.com/ggml-org/whisper.cpp";
echo " cd whisper.cpp"; echo " cd whisper.cpp";
echo " make"; echo " make";
echo " ./examples/yt-wsp.sh https://www.youtube.com/watch?v=1234567890"; echo " ./examples/yt-wsp.sh https://www.youtube.com/watch?v=1234567890";

7
models/README.md
View File

@ -24,8 +24,7 @@ You can now use it like this:
`ggml` models are available from the following locations: `ggml` models are available from the following locations:
- https://huggingface.co/ggerganov/whisper.cpp/tree/main - https://huggingface.co/ggml-org/whisper.cpp/tree/main
- https://ggml.ggerganov.com
### 3. Convert with [convert-pt-to-ggml.py](convert-pt-to-ggml.py) ### 3. Convert with [convert-pt-to-ggml.py](convert-pt-to-ggml.py)
@ -78,7 +77,7 @@ OpenAI format. To read the HF models you can use the [convert-h5-to-ggml.py](con
```bash ```bash
git clone https://github.com/openai/whisper git clone https://github.com/openai/whisper
git clone https://github.com/ggerganov/whisper.cpp git clone https://github.com/ggml-org/whisper.cpp
# clone HF fine-tuned model (this is just an example) # clone HF fine-tuned model (this is just an example)
git clone https://huggingface.co/openai/whisper-medium git clone https://huggingface.co/openai/whisper-medium
@ -96,7 +95,7 @@ Currently, the chunk-based transcription strategy is not implemented, so there c
```bash ```bash
# clone OpenAI whisper and whisper.cpp # clone OpenAI whisper and whisper.cpp
git clone https://github.com/openai/whisper git clone https://github.com/openai/whisper
git clone https://github.com/ggerganov/whisper.cpp git clone https://github.com/ggml-org/whisper.cpp
# get the models # get the models
cd whisper.cpp/models cd whisper.cpp/models

4
models/convert-h5-to-ggml.py
View File

@ -3,7 +3,7 @@
# Usage: # Usage:
# #
# git clone https://github.com/openai/whisper # git clone https://github.com/openai/whisper
# git clone https://github.com/ggerganov/whisper.cpp # git clone https://github.com/ggml-org/whisper.cpp
# git clone https://huggingface.co/openai/whisper-medium # git clone https://huggingface.co/openai/whisper-medium
# #
# python3 ./whisper.cpp/models/convert-h5-to-ggml.py ./whisper-medium/ ./whisper . # python3 ./whisper.cpp/models/convert-h5-to-ggml.py ./whisper-medium/ ./whisper .
@ -12,7 +12,7 @@
# #
# For more info: # For more info:
# #
# https://github.com/ggerganov/whisper.cpp/issues/157 # https://github.com/ggml-org/whisper.cpp/issues/157
# #
import io import io

4
src/whisper.cpp
View File

@ -5529,7 +5529,7 @@ int whisper_full_with_state(
// if length of spectrogram is less than 1.0s (100 frames), then return // if length of spectrogram is less than 1.0s (100 frames), then return
// basically don't process anything that is less than 1.0s // basically don't process anything that is less than 1.0s
// see issue #39: https://github.com/ggerganov/whisper.cpp/issues/39 // see issue #39: https://github.com/ggml-org/whisper.cpp/issues/39
if (seek_end < seek_start + 100) { if (seek_end < seek_start + 100) {
WHISPER_LOG_WARN("%s: input is too short - %d ms < 1000 ms. consider padding the input audio with silence\n", __func__, (seek_end - seek_start)*10); WHISPER_LOG_WARN("%s: input is too short - %d ms < 1000 ms. consider padding the input audio with silence\n", __func__, (seek_end - seek_start)*10);
return 0; return 0;
@ -6375,7 +6375,7 @@ int whisper_full_with_state(
} }
} }
// ref: https://github.com/ggerganov/whisper.cpp/pull/2629 // ref: https://github.com/ggml-org/whisper.cpp/pull/2629
const bool single_timestamp_ending = tokens_cur.size() > 1 && const bool single_timestamp_ending = tokens_cur.size() > 1 &&
tokens_cur[tokens_cur.size() - 2].id < whisper_token_beg(ctx) && tokens_cur[tokens_cur.size() - 2].id < whisper_token_beg(ctx) &&
tokens_cur[tokens_cur.size() - 1].id > whisper_token_beg(ctx); tokens_cur[tokens_cur.size() - 1].id > whisper_token_beg(ctx);