chenyme/Chenyme-AAVT
这是一个全自动（音频）视频翻译项目。利用Whisper识别声音，AI大模型翻译字幕，最后合并字幕视频，生成翻译后的视频。
Supports local model deployment with multiple LLM backends (ChatGPT, Claude, Gemini, DeepSeek) for translation, includes VAD voice activity detection and GPU acceleration via CUDA, and extends beyond subtitling to auto-generate marketing content and provide subtitle-only translation workflows. Built with Streamlit WebUI and available via Docker/Colab for cloud deployment, supporting custom fine-tuned Whisper models alongside word-level segmentation optimization.
2,973 stars. No commits in the last 6 months.
Stars
2,973
Forks
239
Language
Python
License
MIT
Category
Last pushed
Apr 07, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/chenyme/Chenyme-AAVT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jdepoix/youtube-transcript-api
This is a python API which allows you to get the transcript/subtitles for a given YouTube video....
MatteoFasulo/Whisper-TikTok
From AI tools to TikTok video creation using FFMPEG, Microsoft Edge read aloud and OpenAI Whisper model
pszemraj/vid2cleantxt
Python API & command-line tool to easily transcribe speech-based video files into clean text
ArthurFDLR/whisper-youtube
🔉 Youtube Videos Transcription with OpenAI's Whisper
JJWRoeloffs/transcribe_align_textgrid
A small wrapper package around whisper-timestamped. Create force-aligned transcription TextGrids...