whisper.cppOpenAI Whisper 模型的 C/C++ 移植-技术圈

whisper.cpp 是 OpenAI 的 Whisper 自动语音识别 (ASR) 模型的 C/C++ 移植。

特性

没有依赖项的普通 C/C++ 实现

Apple silicon 一等公民 - 通过 Arm Neon 和 Accelerate 框架优化

AVX 内在函数支持 x86 架构

VSX 内在函数支持 POWER 架构

混合 F16 / F32 精度

内存使用率低（Flash Attention）

运行时零内存分配

在 CPU 上运行

C 风格的 API

支持的平台：

Mac OS (Intel and Arm)

Android

Linux / FreeBSD

WebAssembly

Windows (MSVC and MinGW]

Raspberry Pi

模型的整个实现包含在2个源文件中：

张量运算： ggml.h / ggml.c

Transformer 推断： whisper.h / whisper.cpp

这种轻量级的模型实现允许容易地将 OpenAI 的 Whisper 模型集成到不同的平台和应用程序中。

实现细节

核心张量运算在 C 中实现 (ggml.h / ggml.c)

转换器模型和高级 C 风格的 API 是用 C++ 实现的 (whisper.h / whisper.cpp)

main.cpp 中演示了示例用法

stream.cpp 中演示了麦克风的实时音频转录示例

examples 文件夹中提供了各种其他示例

张量运算符针对 Apple 芯片的 CPU 进行了大量优化。根据计算大小，使用 Arm Neon SIMD instrisics 或 CBLAS Accelerate 框架例程。后者对于更大的尺寸特别有效，因为 Accelerate 框架利用现代 Apple 产品中提供的专用 AMX 协处理器。

Quick start 快速开始

首先，下载一个转换为 ggml 格式的 Whisper 模型。例如：



bash ./models/download-ggml-model.sh base.en

构建主要示例并转录一个音频文件，如下所示：



# build the main example

make



# transcribe an audio file

./main -f samples/jfk.wav

要快速演示，只需运行 make base.en ：



$ make base.en



cc  -I.              -O3 -std=c11   -pthread -DGGML_USE_ACCELERATE   -c ggml.c -o ggml.o

c++ -I. -I./examples -O3 -std=c++11 -pthread -c whisper.cpp -o whisper.o

c++ -I. -I./examples -O3 -std=c++11 -pthread examples/main/main.cpp whisper.o ggml.o -o main  -framework Accelerate

./main -h



usage: ./main [options] file0.wav file1.wav ...



options:

  -h,        --help              [default] show this help message and exit

  -t N,      --threads N         [4      ] number of threads to use during computation

  -p N,      --processors N      [1      ] number of processors to use during computation

  -ot N,     --offset-t N        [0      ] time offset in milliseconds

  -on N,     --offset-n N        [0      ] segment index offset

  -d  N,     --duration N        [0      ] duration of audio to process in milliseconds

  -mc N,     --max-context N     [-1     ] maximum number of text context tokens to store

  -ml N,     --max-len N         [0      ] maximum segment length in characters

  -bo N,     --best-of N         [5      ] number of best candidates to keep

  -bs N,     --beam-size N       [-1     ] beam size for beam search

  -wt N,     --word-thold N      [0.01   ] word timestamp probability threshold

  -et N,     --entropy-thold N   [2.40   ] entropy threshold for decoder fail

  -lpt N,    --logprob-thold N   [-1.00  ] log probability threshold for decoder fail

  -su,       --speed-up          [false  ] speed up audio by x2 (reduced accuracy)

  -tr,       --translate         [false  ] translate from source language to english

  -di,       --diarize           [false  ] stereo audio diarization

  -nf,       --no-fallback       [false  ] do not use temperature fallback while decoding

  -otxt,     --output-txt        [false  ] output result in a text file

  -ovtt,     --output-vtt        [false  ] output result in a vtt file

  -osrt,     --output-srt        [false  ] output result in a srt file

  -owts,     --output-words      [false  ] output script for generating karaoke video

  -ocsv,     --output-csv        [false  ] output result in a CSV file

  -of FNAME, --output-file FNAME [       ] output file path (without file extension)

  -ps,       --print-special     [false  ] print special tokens

  -pc,       --print-colors      [false  ] print colors

  -pp,       --print-progress    [false  ] print progress

  -nt,       --no-timestamps     [true   ] do not print timestamps

  -l LANG,   --language LANG     [en     ] spoken language ('auto' for auto-detect)

             --prompt PROMPT     [       ] initial prompt

  -m FNAME,  --model FNAME       [models/ggml-base.en.bin] model path

  -f FNAME,  --file FNAME        [       ] input WAV file path





bash ./models/download-ggml-model.sh base.en

Downloading ggml model base.en ...

ggml-base.en.bin               100%[========================>] 141.11M  6.34MB/s    in 24s

Done! Model 'base.en' saved in 'models/ggml-base.en.bin'

You can now use it like this:



  $ ./main -m models/ggml-base.en.bin -f samples/jfk.wav





===============================================

Running base.en on all samples in ./samples ...

===============================================



----------------------------------------------

[+] Running base.en on samples/jfk.wav ... (run 'ffplay samples/jfk.wav' to listen)

----------------------------------------------



whisper_init_from_file: loading model from 'models/ggml-base.en.bin'

whisper_model_load: loading model

whisper_model_load: n_vocab       = 51864

whisper_model_load: n_audio_ctx   = 1500

whisper_model_load: n_audio_state = 512

whisper_model_load: n_audio_head  = 8

whisper_model_load: n_audio_layer = 6

whisper_model_load: n_text_ctx    = 448

whisper_model_load: n_text_state  = 512

whisper_model_load: n_text_head   = 8

whisper_model_load: n_text_layer  = 6

whisper_model_load: n_mels        = 80

whisper_model_load: f16           = 1

whisper_model_load: type          = 2

whisper_model_load: mem required  =  215.00 MB (+    6.00 MB per decoder)

whisper_model_load: kv self size  =    5.25 MB

whisper_model_load: kv cross size =   17.58 MB

whisper_model_load: adding 1607 extra tokens

whisper_model_load: model ctx     =  140.60 MB

whisper_model_load: model size    =  140.54 MB



system_info: n_threads = 4 / 10 | AVX = 0 | AVX2 = 0 | AVX512 = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 0 | VSX = 0 |



main: processing 'samples/jfk.wav' (176000 samples, 11.0 sec), 4 threads, 1 processors, lang = en, task = transcribe, timestamps = 1 ...





[00:00:00.000 --> 00:00:11.000]   And so my fellow Americans, ask not what your country can do for you, ask what you can do for your country.





whisper_print_timings:     fallbacks =   0 p /   0 h

whisper_print_timings:     load time =   113.81 ms

whisper_print_timings:      mel time =    15.40 ms

whisper_print_timings:   sample time =    11.58 ms /    27 runs (    0.43 ms per run)

whisper_print_timings:   encode time =   266.60 ms /     1 runs (  266.60 ms per run)

whisper_print_timings:   decode time =    66.11 ms /    27 runs (    2.45 ms per run)

whisper_print_timings:    total time =   476.31 ms

该命令下载转换为自定义 ggml 格式的 base.en 模型，并对文件夹 samples 中的所有 .wav 样本运行推理。

有关详细的使用说明，请运行： ./main -h

请注意，主要示例当前仅使用 16 位 WAV 文件运行，因此请确保在运行该工具之前转换您的输入。例如，您可以像这样使用 ffmpeg ：



ffmpeg -i input.mp3 -ar 16000 -ac 1 -c:a pcm_s16le output.wav

内存使用状况

Model	Disk	Mem	SHA
tiny	75 MB	~125 MB	`bd577a113a864445d4c299885e0cb97d4ba92b5f`
base	142 MB	~210 MB	`465707469ff3a37a2b9b8d8f89f2f99de7299dac`
small	466 MB	~600 MB	`55356645c2b361a969dfd0ef2c5a50d530afd8d5`
medium	1.5 GB	~1.7 GB	`fd9727b6e1217c2f614f9b698455c4ffd82463b4`
large	2.9 GB	~3.3 GB	`0f4c8e34f21cf1a914c59d8b3ce882345ad349d6`