0.2.1

GargantuaX/gemini-watermark-remover0.2.1Nov 30, 2024by edwko

AI Summary

This release introduces support for the ExLlamaV2 model and integrates Whisper for automatic transcription when speaker text is missing.

Key Highlights

Integrated support for ExLlamaV2 model.
Whisper integration for generating speakers automatically when no transcript is provided.
New parameters `whisper_model` and `whisper_device` added to the `create_speaker` method.

New Features

ExLlamaV2 support.
Automatic text transcription using Whisper when the `transcript` parameter is set to 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
   )
   ```