whisper-standalone-win

Purfview长期未更新

免装 Python 的 Whisper 与 Faster-Whisper 独立可执行程序，解压即用，直接做语音转文字、字幕生成和说话人分离。

Whisper & Faster-Whisper standalone executables for those who don't want to bother with Python.

Pro发布于 2025-11-07 19:21 UTC3,233star +1 / 7 天168fork同步于 2026-11-10 23:42 UTC

语音识别语音转文字字幕生成说话人分离免Python

对比 GitHub asr ctranslate2 diarization faster-whisper openai

怎么上手

由 README 提炼，执行前请确认

原文

faster-whisper-xxl.exe "D:\videofile.mkv" --language English --model medium --output_dir source

硬件要求按 README 说明

README 未给出具体显存要求；Faster-Whisper 版支持 x86-64 的 Windows 7、Linux v5.4、macOS v10.15 及以上，Faster-Whisper-XXL 需 Windows 10、Linux v5.15 及以上，Whisper 版需 Windows 10 及以上；检测到 CUDA 时自动使用 GPU。

需要 CUDA

下载：源码 zip·GitHub Releases（安装包）本站不镜像安装包

项目说明

由 README 自动翻译提炼

没人工点评？写下你的经验

免装 Python 的 Whisper 与 Faster-Whisper 命令行可执行版，直接跑语音转写和字幕生成

免装 Python 的 Whisper 与 Faster-Whisper 独立可执行程序，解压即用，直接做语音转文字、字幕生成和说话人分离。

核心能力

提供 Whisper 与 Faster-Whisper 的独立可执行文件，无需 Python 环境
检测到 CUDA 时自动切换到 GPU 运行
默认在程序同目录 _models 下查找模型，也可自动下载
XXL 版支持 MDX23 人声分离预处理与多种 VAD 方案
XXL 版支持说话人分离（Speaker Diarization）

容易踩的坑

可执行文件和库需从 Releases 页面单独下载，不要复制到 Windows 系统文件夹；模型默认放在程序同目录的 _models\faster-whisper-<模型名> 下，首次使用需下载；转写质量建议不要用小于 medium 的模型。

内容由模型根据 README 生成，可能不完整或不准确，以官方文档为准。看原文 README

最近发版

5 个版本Pro

全部 release

ProFaster-Whisper-XXL Pro r3.256.1最新正式版2025-11-07 · 2025-11-07 19:21 UTC
Fixed: --realign "UnicodeDecodeError" error.
Fixed: --realign error if there is more than one line per sub. Fixed: --realign "File not found" error.
Fixed: ImportError: libctranslate2-d3638643.so.4.4.0 [Linux] Fixed: ffmpeg: error while loading shared libraries [Linux] Hide: "not compiled with flash attention" warning.
Fixed: "cuda:1" didn't work with MDX [untested, "r245.3" fix was broken] New VAD models: silero_v6_fw, silero_v6 [patched], nemo_v2, ten [its threshold is offset by +0.2] Change: --vad_method default is set to ten Change: Batched mode has few improvements Change: --compute_type defaults to default if CUDA, else auto. Updated: torch to 2.8.0+cu128 [to support 50xx GPUs on torch models] Updated: onnxruntime_gpu to 1.21.1 [cuDNN 9.x] Updated: pyinstaller to 6.16.0

Faster-Whisper-XXL Pro
Faster-Whisper-XXLFaster-Whisper-XXL r245.42024-03-27 · 2024-03-27 01:04 UTC
查看更新说明
Standalone Faster-Whisper implementation using optimized CTranslate2 models.

Includes all Standalone Faster-Whisper features + some additional ones. Read here. Last included commit: #245 Faster-Whisper-XXL includes all needed libs.

Some new stuff in r245.4:

Fixed: 'unload_model' error when using batched inference

Some new stuff in r245.3:

Fixed: Model didn't free VRAM when --model_preload False Fixed: "cuda:1" didn't work with MDX Fixed: Some issues in "One Click Transcribe.bat" Fixed: Matplotlib backend error [Colab] Fixed: cuDNN libs not found error [Linux] Changed: --ff_mdx_kim2 to --ff_vocal_extract mdx_kim2 Changed: --mdx_device to --voc_device Added: distil-large-v3.5 model Updated: pyinstaller to 6.12.0

Link to the changelog.
faster-whisperFaster-Whisper r192.32023-08-15 · 2023-08-15 16:04 UTC
查看更新说明
Standalone Faster-Whisper implementation using optimized CTranslate2 models.

GPU execution requires cuBLAS and cuDNN 8.x libs for CUDA v11.x .

Last included commit: #192

Note:

This release branch is deprecated, use Faster-Whisper-XXL.

Link to the changelog.
Whisper-OpenAIWhisper-OpenAI r1502023-05-30 · 2023-05-30 22:49 UTC
查看更新说明
Standalone Whisper. Last included commit: #150.

Whisper-OpenAI includes all needed libs.

libscuBLAS and cuDNN2023-05-17 · 2023-05-17 21:30 UTC

查看更新说明

Place libs in the same folder where Faster-Whisper executable is. Or to: Windows: To System32 dir. Linux: To dir in LD_LIBRARY_PATH env.

CUDA11_v2 is the last with support for GPUs with Kepler chip.

CUDA11_v2: - cuBLAS.and.cuDNN____v11.11.3.6__v8.7.0.84
CUDA11_v3: - cuBLAS.and.cuDNN____v11.11.3.6__v8.9.6.50
CUDA11_v4: - cuBLAS.and.cuDNN____v11.11.3.6__v8.9.7.29

CUDA12_v1: - cuBLAS.and.cuDNN____v12.4.5.8___v8.9.7.29

CUDA12_v2: - cuBLAS.and.cuDNN____v12.4.5.8___v9.5.1.17
CUDA12_v3: - cuBLAS.and.cuDNN____v12.8.4.1___v9.8.0.87

用户点评

登录用户的真实使用记录，可按版本和硬件筛选

共 0 条

还没有人点评。第一个说出真实体验的人最有价值。

README 原文

未翻译

在 GitHub 打开

alt text

Standalone executables of OpenAI's Whisper & Faster-Whisper for those who don't want to bother with Python.

Faster-Whisper - executables are x86-64 compatible with Windows 7, Linux v5.4, macOS v10.15 and above.
Faster-Whisper-XXL - the last executables are x86-64 compatible with Windows 10, Linux v5.15 and above.
Faster-Whisper-XXL Pro - as above. Special non-public version for the donators.
Whisper - executables are x86-64 compatible with Windows 10 and above.

Meant to be used in command-line interface or in programs like:
Subtitle Edit, Tero Subtitler, FFAStrans, AviUtl, PotPlayer
Faster-Whisper is much faster & better than OpenAI's Whisper, and it requires less RAM/VRAM.

Usage examples:

faster-whisper-xxl.exe "D:\videofile.mkv" --language English --model medium --output_dir source
faster-whisper-xxl.exe "D:\Folder" -l en -m turbo --sentence --batch_recursive
faster-whisper-xxl.exe "D:\videofile.mkv" -l ja -m medium --task translate --standard -o source
faster-whisper-xxl.exe --help

Notes:

Executables & libs can be downloaded from Releases. [at the right side of this page]
Don't copy programs to the Windows' folders! [run as Administrator if you did]
Programs automatically will choose to work on GPU if CUDA is detected.
For decent transcription use not smaller than medium model.
Guide how to run the command line programs: https://www.youtube.com/watch?v=A3nwRCV-bTU

Standalone Whisper info:

Vanilla Whisper, compiled as is - no changes to the original code.
A reference implementation, stagnant development, atm maybe useful for some tests.

Standalone Faster-Whisper info:

Some defaults are tweaked for movies transcriptions and to make it portable.
Features various new experimental settings and tweaks.
Shows the progress bar in the title bar of command-line interface. [or it can be printed with -pp]
By default it looks for models in the same folder, in path like this -> _models\faster-whisper-medium.
Models are downloaded automatically or can be downloaded manually from: Systran & Purfview
Deprecated. Use Faster-Whisper-XXL

Standalone Faster-Whisper-XXL info:

Includes all Standalone Faster-Whisper features + the additional ones, for example:
Preprocess audio with MDX23 Kim_vocal_v2 vocal extraction model.
Alternative VAD methods: 'silero_v3', 'silero_v4', 'silero_v5', 'pyannote_v3', 'pyannote_onnx_v3', 'auditok', 'webrtc'.
Speaker Diarization.
Read more about new features in the Discussions' thread.

Standalone Faster-Whisper-XXL Pro info:

Special non-public version for the donators.
Includes some new advanced features, there is the log: the Discussions' thread.