add deepspeed

remove evaluation, no need function

fix: Update model name in EnhancedWav2Vec2CharacterASR constructor for improved performance

Enhance ASR and feedback mechanisms with Vietnamese pronunciation tips

update: new model xlsr

feat: Implement ultra-optimizations for pronunciation assessment system

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

feat: Implement performance optimizations in speaking_route.py

Enhance Vietnamese feedback generation with actionable insights and specific improvement strategies. Refine overall feedback based on score ranges, provide detailed guidance for problematic words and phonemes, and suggest clear next steps for users to improve their pronunciation skills.

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

Refactor code structure for improved readability and maintainability

feat: add Levenshtein package to requirements for improved string comparison

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: add text cleaning functionality for TTS service to enhance input processing

feat: update device selection in Wave2Vec2Inference to support GPU usage and enhance performance

fix: reorganize import statements for clarity and remove unused imports

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

feat: implement Wav2Vec2 character-level ASR with ONNX and Transformers support, add phoneme comparison and feedback generation

fix: update import statement for BaseModel in agent.py and add timing logs in speaking_controller.py

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 nltk to requirements for natural language processing

feat: install ffmpeg in Dockerfile

chore: remove compiled Python bytecode file

feat: add speaking route for pronunciation assessment API

update: evaluation

feat: set Teaching Agent as default and enhance interaction prompts

feat: evaluation when end

feat: text to speech for AI response

prompt: at handoff trigger for guiding agent roleplay

prompt: hallucination at repsonse length

update prompt

prompt: add markdown and agent name

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

update follow-up questions in scenarios for clarity and relevance

update prompt new tối nay

update prompt claude

first commit

deployment: update

Update Dockerfile

Upload 74 files