0.2.1

jgraph/drawio0.2.1Nov 30, 2024by edwko

AI Summary

Adds support for the ExLlamaV2 backend and integrates Whisper for automatic transcription when generating speakers.

Key Highlights

Support for ExLlamaV2 backend
Whisper Integration for automatic speaker generation
Automatic transcription when transcript is set to None

New Features

ExLlamaV2 support
Whisper integration

Full Release Notes

### Release Notes v0.2.1

#### New Features and Improvements:

1. **Support for ExLlamaV2**  
   - Integrated support for ExLlamaV2
   - Pull request: #37

2. **Whisper Integration for Speaker Generation**  
   - Added Whisper-based transcription for generating speakers when no transcript is provided.  
   - Suggested in: #28 
   - Now, if `transcript` is set to `None`, the text will be automatically transcribed using Whisper.  

   ```python
   def create_speaker(
       self, 
       audio_path: str, 
       transcript: str = None, 
       whisper_model: str = "turbo",
       whisper_device = None
   )
   ```