add deepspeed

Enhance ASR and feedback mechanisms with Vietnamese pronunciation tips

update: new model xlsr

feat: Implement Whisper model preloading during FastAPI startup for optimized performance

feat: Implement performance optimizations in speaking_route.py

feat: implement new IPA assessment API with detailed phoneme analysis and Vietnamese-specific feedback

Refactor code structure for improved readability and maintainability

Implement enhanced pronunciation assessment system with Wav2Vec2 support

Implement Lesson Practice 2 Agent with state management and routing logic; add practice and teaching agent functions; create prompts for conversation and teaching; establish pronunciation API with lesson data and search functionality.

feat: refactor Wav2Vec2 character ASR to support quantization and improve model loading

Add Wav2Vec2 model conversion and inference to ONNX format

Implement code changes to enhance functionality and improve performance

Implement feature X to enhance user experience and fix bug Y in module Z

feat: add speaking route for pronunciation assessment API

update: evaluation

feat: evaluation when end

feat: text to speech for AI response

prompt: optimize

feat: audio v2 multi agent

remove conversation management

Add trim_history function and update lesson chat route to handle text and audio inputs

Refactor roleplay agent implementation and update session handling for improved message processing

Enhance roleplay API to support audio messages and add comprehensive test cases

Add lesson management functionality with JSON data integration and response models

Implement lesson practice agent and related functionality

first commit

deployment: update

Upload 74 files