interviewtranscriptionqualitative-researchaudio-transcriptionpyannotewhisper-cpp UpdatedApr 24, 2025 Python 「妙幕」是一款跨平台客户端工具,可以批量为视频或者音频生成字幕文件,并支持对字幕进行翻译,支持百度、火山、openai、ollama、deepseek 等多家
GitHub is where people build software. More than 150 million people use GitHub to discover, fork, and contribute to over 420 million projects.
配置Whisper.cpp 老规矩,运行git命令来克隆Whisper.cpp项目: git clone https://github.com/ggerganov/whisper.cpp.git 随后进入项目的目录: cd whisper.cpp 项目默认的基础模型不支持中文,这里推荐使用medium模型,通过shell脚本进行下载: bash ./models/download-ggml-model.sh medium 下载完成后,会在项目的models...
➜ whisper.cpp git:(master) ./main -osrt -m ./models/ggml-medium.bin -f samples/test1.wav -l zhwhisper_init_from_file_no_state: loading model from './models/ggml-medium.bin'whisper_model_load: loading modelwhisper_model_load: n_vocab = 51865whisper_model_load: n_audio_ctx = ...
conda activate python3112 1. 首次执行上面的命令可能需要使用conda init,执行完毕后关闭当前shell脚本命令,再重新打开执行激活环境的命令 退出虚拟环境 conda deactivate 1. 注意:看上面我是直接在CMD下使用的命令,比如如果你想在git bash下运行conda的话
1.OpenAI的Whisper模型:whisper.cpp 30.1k⭐ 项目地址:https://github.com/ggerganov/whisper.cpp ...
【小沐学Python】Python实现语音识别(Whisper,测试),1、简介https://github.com/openai/whisper3、测试3.1命令测试whisperaudio.mp3以上whisperaudio.mp3的命令形式是最简单的一种,它默认使用的是small模式的模型转写,我们还可以使用更高等级的模型来提高正确率。比如
pip install git+https://github.com/abdeladim-s/pywhispercpp CoreML support Thanks to@tangm, using CoreML is now supported: To build and install, clone the repository and run the following commands: exportCMAKE_ARGS="-DWHISPER_COREML=1"python -m build --wheel#in this repository to build...
README Python bindings for whisper.cpp pip install git+https://github.com/o4dev/whispercpp.py from whispercpp import Whisper w = Whisper('tiny') result = w.transcribe("myfile.mp3") text = w.extract_text(result) Note: default parameters might need to be tweaked. See Whispercpp.pyx.About...
【小沐学Python】Python实现语音识别(Whisper,简介),1、简介https://github.com/openai/whisper1.1whisper简介Whisper是一种通用的语音识别模型。它是在包含各种音频的大型数据集上训练的,也是一个多任务模型,可以执行多语言语音识别、语音翻译和语言识别。OpenAI在20