0.2.1

OpenBMB/MiniCPM-V0.2.1Nov 30, 2024by edwko

AI Summary

OuteTTS v0.2.1 adds ExLlamaV2 support and integrates Whisper for automatic speaker transcription when no transcript is provided.

Key Highlights

Integrated support for ExLlamaV2 backend
Whisper-based transcription for generating speakers
Automatic transcription when transcript is None
Configurable Whisper model selection (default: turbo)
Flexible Whisper device configuration

New Features

ExLlamaV2 backend integration
Whisper-based speaker generation with automatic transcription
Configurable Whisper model and device selection
Improved speaker creation flexibility

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
   )
   ```