Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/chaoticbyte/audio-summarize
An audio summarizer (faster-whisper and BART glued together)
https://github.com/chaoticbyte/audio-summarize
ai ai-summarizer audio bart ctranslate2 faster-whisper nlp speech-to-text summarization whisper
Last synced: 3 months ago
JSON representation
An audio summarizer (faster-whisper and BART glued together)
- Host: GitHub
- URL: https://github.com/chaoticbyte/audio-summarize
- Owner: ChaoticByte
- License: mit
- Created: 2024-08-13T18:29:06.000Z (5 months ago)
- Default Branch: main
- Last Pushed: 2024-08-16T18:19:50.000Z (5 months ago)
- Last Synced: 2024-10-09T19:05:19.554Z (3 months ago)
- Topics: ai, ai-summarizer, audio, bart, ctranslate2, faster-whisper, nlp, speech-to-text, summarization, whisper
- Language: Python
- Homepage:
- Size: 17.6 KB
- Stars: 1
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# audio-summarize
An audio summarizer that glues together [faster-whisper](https://github.com/SYSTRAN/faster-whisper) and [BART](https://huggingface.co/facebook/bart-large-cnn).
## Supported Languages
Only English summarization is supported.
## Dependencies
- Python 3 (tested: 3.12)
## Setup
Create a virtual environment for python, activate it and install the required python packages:
```bash
python3 -m venv .venv
source .venv/bin/activate
pip3 install -r requirements.txt
```
## Run
1. In your terminal, make shure you have your python venv activated
2. Run audio-summarize.py
### Usage
```
./audio-summarize.py -i filepath -o filepath [-m name]
[--summin n] [--summax n] [--segmax n]
options:
-h, --help show this help message and exit
--summin n The minimum lenght of a segment summary [10] (min: 5)
--summax n The maximum lenght of a segment summary [90] (min: 5)
--segmax n The maximum number of tokens per segment [375] (5 - 500)
-m name The name of the whisper model to be used [small.en]
-i filepath The path to the media file
-o filepath Where to save the output text to
```
Example:
```bash
./audio-summarize.py -i ./tmp/test.webm -o ./tmp/output.txt
```
## How does it work?
To summarize a media file, the program executes the following steps:
1. Convert and transcribe the media file using [faster-whisper](https://github.com/SYSTRAN/faster-whisper), using [ffmpeg](https://www.ffmpeg.org/) and [ctranslate2](https://github.com/OpenNMT/CTranslate2/) under the hood
2. Semantically split up the transcript into segments using [semantic-text-splitter](https://github.com/benbrandt/text-splitter) and the tokenizer for BART
3. Summarize each segment using BART ([`facebook/bart-large-cnn`](https://huggingface.co/facebook/bart-large-cnn))
4. Write the results to a text file