transcriptionstream - GitLite

KO | EN

gitlite — search

#javascript #python #hacktoberfest #react #ai #go #deep-learning #docker #macos #nodejs #cli #kubernetes #awesome-list #openai

transcriptionstream

(★ 946)

turnkey self-hosted offline transcription and diarization service with llm summary

파일 탐색기

최종 버전 다운로드 (.zip)

- auto-summary.py
- Dockerfile
- index-single.py
- test.wav
- transcribe_example_d.sh
- ts-control.sh
- ts-summarize.py
- - alerts.js
  - audioControls.js
  - fileHandling.js
  - gears.png
  - gears.svg
  - styles.css
  - transcription.js
- - alert.html
  - alerts.html
  - controls.html
  - index.html
  - transcription.html
  - upload.html
- app.py
- Dockerfile
- requirements.txt
.env
.gitignore
docker-compose-nobuild.yml
docker-compose.yml
install.sh
LICENSE.txt
README.md
run.sh
start-nobuild.sh

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/transcriptionstream/transcriptionstream

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd transcriptionstream

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Docker

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Docker Desktop 컨테이너를 빌드하고 실행하려면 필요합니다. 설치 후 실행해서 백그라운드에 켜두세요.

docker compose up -d --build

정의된 모든 컨테이너(서버, DB 등)를 한 번에 빌드하고 백그라운드에서 실행합니다.

✅ 터미널에 docker compose ps 를 입력해 컨테이너들이 Up 상태인지 확인하세요. README에 포트 번호가 적혀있다면 브라우저에서 http://localhost:포트번호 로 접속해보세요.

3. Python

쉬움

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

pip install -r ts-web/requirements.txt

requirements.txt 등에 명시된 파이썬 라이브러리를 설치합니다.

python <실행할 파일명>.py # README에서 정확한 실행 파일명을 확인하세요

파이썬 스크립트(또는 모듈)를 실행합니다.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Transcription Stream Community Edition
Created by [https://transcription.stream](https://transcription.stream) with special thanks to [MahmoudAshraf97](https://github.com/MahmoudAshraf97) and his work on [whisper-diarization](https://github.com/MahmoudAshraf97/whisper-diarization/), and to [jmorganca](https://github.com/jmorganca/ollama) for [Ollama](https://ollama.com/) and its amazing simplicity in use.

## Overview
Transcription Stream is a turnkey self-hosted diarization service that works completely offline. Out of the box it includes:
- drag and drop diarization and transcription via SSH
- a web interface for upload, review, and download of files
- summarization with Ollama and Mistral
- Meilisearch for full text search

A web interface and SSH drop zones make this simple to use and implement into your workflows. Ollama allows for a powerful toolset, limited only by your prompt skills, to perform complex operations on your transcriptions. Meiliesearch adds ridiculously fast full text search.

Use the web interface to upload, listen to, review, and download output files, or drop files via SSH into `transcribe` or `diarize`. Files are processed with output placed into a named and dated folder. Have a quick look at the <a href="https://www.youtube.com/watch?v=3RufeOjnlcE">install</a> and <a href="https://www.youtube.com/watch?v=pbZ8o7_MjG4">ts-web walkthrough</a> videos for a better idea.

<div align="center">
<h3>ssh upload and transcribed</h3>
<img src="https://transcription.stream/ts-sshupload.png" width="33%" style="vertical-align: top;" alt="upload file to be diarized to the diarize folder">  <img src="https://transcription.stream/ts-sshtranscribed.png" width="33%" style="vertical-align: top;" alt="transcribed files in their folders">

<h3>ts-web interface</h3>
<a href="https://www.youtube.com/watch?v=pbZ8o7_MjG4">
<img src="https://transcription.stream/ts-web.png" width="66%" alt="Example Image">
</a>
<h3>ts-gpu diarization example </h3>
<a href="https://www.youtube.com/watch?v=UAgbcZjR4mM">
    <img src="https://transcription.stream/videothumb.png" alt="watch video on youtube" style="width: 66%;">
  </a>
</div>
<div align="center">
<h3>mistral summary</h3>
<img src="https://transcription.stream/summary.png" alt="local ollama mistral summary" style="width: 50%;">
</div>

```
prompt_text = f"""
Summarize the transcription below. Be sure to include pertinent information about the speakers, including name and anything else shared.
Provide the summary output in the following style

Speakers: names or identifiers of speaking parties
Topics: topics included in the transcription
Ideas: any ideas that may have been mentioned
Dates: dates mentioned and what they correspond to
Locations: any locations mentioned
Action Items: any action items

Summary: overall summary of the transcription

The transcription is as follows

{transcription_text}

"""
```

**Prerequisite: NVIDIA GPU**
> **Warning:** The resulting ts-gpu image is ~26GB and might take a hot second to create

## Quickstart (no build)
### Pulls all docker images and starts services
```bash
./start-nobuild.sh
```

## Build and Run Instructions
> If you'd like to build the images locally
### Automated Install and Run
```bash
chmod +x install.sh;
./install.sh;
```
### Run
```bash
chmod +x run.sh;
./run.sh
```

## Additional Information

### Ports
- **SSH:** 22222
- **HTTP:** 5006
- **Ollama:** 11434
- **Meilisearch:** 7700

### SSH Server Access
- **Port:** 22222
- **User:** `transcriptionstream`
- **Password:** `nomoresaastax`
- **Usage:** Place audio files in `transcribe` or `diarize`. Completed files are stored in `transcribed`.

### Web Interface
- **URL:** [http://dockerip:5006](http://dockerip:5006)
- **Features:**
  - Audio file upload/download
  - Task completion alerts with interactive links
  - HTML5 web player with speed control and transcription highlighting
  - Time-synced transcription scrubbing/highlighting/scrolling

### Ollama api
- **URL:** [http://dockerip:11434](http://dockerip:11434)
- change the prompt used, in `/ts-gpu/ts-summarize.py`

### Meilisearch api
- **URL:** [http://dockerip:7700](http://dockerip:7700)

> **Warning:** This is example code for example purposes and should not be used in production environments without additional security measures.

### Customization and Troubleshooting
- Update variables in the .env file
- Change the password for `transcriptionstream` in the `ts-gpu` Dockerfile.
- Update the Ollama api endpoint IP in .env if you want to use a different endpoint
- Update the secret in .env for ts-web
- Use .env to choose which models are included in the initial build.
- Change the prompt text in ts-gpu/ts-summarize.py to fit your needs. Update ts-web/templates/transcription.html if you want to call it something other than summary.
- 12GB of vram may not be enough to run both whisper-diarization and ollama mistral. Whisper-diarization is fairly light on gpu memory out of the box, but Ollama's runner holds enough gpu memory open causing the diarization/transcription to run our of CUDA memory on occasion. Since I can't run both on the same host reliably, I've set the batch size for both whisper-diarization and whisperx to 16, from their default 8, and let a m series mac run the Ollama endpoint. 
### To-do
- Need to fix an issue with ts-web that throws an error to console when loading a transcription when a summary.txt file does not also exist. Lots of other annoyances with ts-web, but it's functional.
- Need to add a search/control interface to ts-web for Meilisearch