https://github.com/assemblyai-solutions/async-chunking
https://github.com/assemblyai-solutions/async-chunking
Last synced: over 1 year ago
JSON representation
- Host: GitHub
- URL: https://github.com/assemblyai-solutions/async-chunking
- Owner: AssemblyAI-Solutions
- Created: 2024-02-14T03:59:12.000Z (over 2 years ago)
- Default Branch: master
- Last Pushed: 2024-02-14T04:05:26.000Z (over 2 years ago)
- Last Synced: 2025-01-24T04:53:32.925Z (over 1 year ago)
- Language: Python
- Size: 27.8 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Async Chunking ASR
### How to get started
1. Install dependencies
```python
pip install -r requirements.txt
```
2. Start [Redis Server](https://redis.io/docs/ui/insight/) on CLI (Current config uses localhost)
```shell
redis-server
```
3. Run ```output.py```, this is responsible for printing transcripts in order
```
python3 output.py
```
4. Run ```app.py```, this is responsible for listening for AssemblyAI Webhooks, sent on transcript completion.
```
python3 app.py
```
5. Run ```chunked_asr.py```, this is responsible for pulling Audio from URL and chunking into smaller files using Voice Activity Detection (VAD)
```
python3 chunked_asr.py
```
#### *Disclaimer:*
- This is for demo purposes
- Please contact sflamini@assemblyai.com for support!