0.2.1

zumerlab/snapdom0.2.1Nov 30, 2024by edwko

AI Summary

This release adds support for ExLlamaV2 and integrates Whisper for automatic speaker generation when transcripts are not provided.

Key Highlights

Support for ExLlamaV2
Whisper integration for automatic speaker transcription

New Features

ExLlamaV2 integration
Whisper-based transcription for speaker generation
Automatic transcript handling when `transcript` is None

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
   )
   ```