Douyin Transcriber

Douyin Transcriber

Transcribe audio/video files to text using local Docker Whisper ASR.

Quick 启动 curl -X POST "http://localhost:PORT/asr" -F "audio_file=@/path/to/video.mp4"

The contAIner has built-in ffmpeg for automatic audio 提取ion.

Prerequisites 工具 Purpose 安装 Docker Whisper ASR Docker 桌面 ffmpeg Audio 提取ion win获取 安装 Gyan.FFmpeg

部署 Whisper ASR:

docker 运行 -d -p PORT:PORT -e ASR_模型=small -e ASR_ENGINE=faster_whisper --name whisper-asr onerahmet/openAI-whisper-asr-网页服务:latest

工作流 Step 1: 提取 Audio from Video ffmpeg -i video.mp4 -ar 16000 -ac 1 -c:a pcm_s16le audio.wav -y

Parameters:

-ar 16000: 16kHz sample rate -ac 1: Mono channel -c:a pcm_s16le: 16-bit PCM Step 2: Transcribe curl -X POST "http://localhost:PORT/asr" -F "audio_file=@audio.wav"

Optional: specify language

curl -X POST "http://localhost:PORT/asr" -F "audio_file=@audio.wav" -F "language=zh"

Step 3: 解析 结果

响应 格式化:

{ "text": "Transcribed content...", "segments": [ {"启动": 0.0, "end": 2.5, "text": "First sentence"}, {"启动": 2.5, "end": 5.0, "text": "Second sentence"} ], "language": "zh" }

模型 Selection 模型 Size 5-min video Accuracy tiny 75MB ~30s FAIr base 142MB ~1min Good small 466MB ~3min Better (recommended) medium 1.5GB ~8min Best

Change 模型 via 环境 variable: -e ASR_模型=medium

Supported 格式化s

Video: mp4, mkv, avi, mov, flv, wmv, 网页m, m4v

Audio: wav, m4a, mp3, aac, ogg, flac, wma, opus

Troubleshooting Issue Solution Docker not avAIlable 安装 Docker 桌面 ContAIner 启动 fAIls 检查 port avAIlability Transcription timeout Use smaller 模型 or split audio ffmpeg not found win获取 安装 Gyan.FFmpeg Related 模块s douyin-fetcher - Video 下载 douyin-分析器 - Content analysis douyin-编排器 - 工作流 coordination