5 Matching Annotations
  1. Jun 2025
  2. github.com github.com
    169/intelli-video: OpenAI API and Whisper based Video Translation
    1
    1. bamanzi 06 Jun 2025

      能力 - 语音转写：支持OpenAI Whisper (本地 & 在线API） - 翻译: 未说明基于什么引擎实现

      问题: - 似乎不支持单独的【翻译字幕文件】任务

      audio2srt whisper openai_api
    Visit annotations in context

    Tags

    Annotators

    URL

    github.com/169/intelli-video
  3. github.com github.com
    chidiwilliams/buzz: Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.
    1
    1. bamanzi 06 Jun 2025

      能力 - 语音转录: 基于whisper模型（可本地，也可用OpenAI Whisper API） - 字幕翻译: 支持ollama 和 LM Studio （其实是基于【兼容OpenAI API】设计的 https://chidiwilliams.github.io/buzz/zh/docs/usage/translations ）

      安装与部署: 基于python包 - 对MacOS和Windows均提供了一键安装包 - 对Linux提供了flatpak和snap包

      audio2srt srt2zh ollama lm_studio whisper openai_api
    Visit annotations in context

    Tags

    Annotators

    URL

    github.com/chidiwilliams/buzz
  4. github.com github.com
    bushkarl/videoprocessor: 智能视频处理系统
    1
    1. bamanzi 06 Jun 2025

      👎 2024年12月后无更新了，估计作者已经弃坑

      功能: - 音频转写采用whisper模型 （基于python包openai-whisper实现，需要pytorch支持） - 翻译只支持Azure Translator API

      部署: 基于python 和 ffmpeg

      whisper pytorch python ffmpeg srt2zh audio2srt
    Visit annotations in context

    Tags

    Annotators

    URL

    github.com/bushkarl/videoprocessor
  5. github.com github.com
    WEIFENG2333/VideoCaptioner: 🎬 卡卡字幕助手 | VideoCaptioner - 基于 LLM 的智能字幕助手 - 视频字幕生成、断句、校正、字幕翻译全流程处理！- A powered tool for easy and efficient video subtitling.
    1
    1. bamanzi 06 Jun 2025

      能力: - 语音转录支持本地(WhisperCpp/FasterWhisper) 和在线（B接口/J接口??） - 字幕翻译支持传统引擎和LLM - 传统引擎: DeepL/微软/谷歌 - LLM: Ollama、DeepSeek、硅基流动以及【OpenAI兼容接口】 （配套提供LLM API中转站）

      安装部署 - Windows提供一键安装包 - MacOS需要自行基于python搭建，且作者说未验证过 👎 。另外本地 whisper 功能尚不支持macos）

      windows whisper google siliconcloud deepseek ollama python srt2zh audio2srt
    Visit annotations in context

    Tags

    Annotators

    URL

    github.com/WEIFENG2333/VideoCaptioner
  6. Mar 2023
  7. github.com github.com
    openai/whisper: Robust Speech Recognition via Large-Scale Weak Supervision
    1
    1. polarislee 14 Mar 2023
      Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification.

      Whisper는 범용 음성 인식 모델입니다. 다양한 오디오의 대규모 데이터 세트를 학습하고 다국어 음성 인식, 음성 번역, 언어 식별을 수행할 수 있는 멀티태스킹 모델이기도 합니다.

      ASR Open Source Whisper 음성인식 openAI Whisper API
    Visit annotations in context

    Tags

    Annotators

    URL

    github.com/openai/whisper