Spaces:
Sleeping
Sleeping
Commit History
-
feat: Implement performance optimizations in speaking_route.py
- Added asynchronous processing for post-assessment tasks to reduce processing time. - Introduced shared instances for G2P and ThreadPoolExecutor to improve resource management. - Implemented caching for G2P results to avoid redundant computations. - Enhanced IPA assessment processing with parallel execution for character analysis, phoneme scoring, and focus phonemes analysis. - Created a performance testing script to validate optimizations and measure improvements. - Documented optimization strategies and performance metrics in PERFORMANCE_OPTIMIZATION.md.c9fd875 -
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.
b9c5d04 -
feat: implement new IPA assessment API with detailed phoneme analysis and Vietnamese-specific feedback
45a0e83 -
Refactor code structure for improved readability and maintainability
85fa45c
-
feat: add Levenshtein package to requirements for improved string comparison
2877f54 -
Implement enhanced pronunciation assessment system with Wav2Vec2 support
- Added Wav2Vec2CharacterASR class for character-level ASR using Wav2Vec2 model. - Integrated SimpleG2P for grapheme-to-phoneme conversion. - Developed WordAnalyzer for analyzing word-level pronunciation accuracy. - Created PhonemeComparator to compare reference and learner phoneme sequences. - Introduced SimpleFeedbackGenerator for generating actionable feedback in Vietnamese. - Implemented SimplePronunciationAssessor as the main interface for pronunciation assessment. - Added test scripts for backward compatibility and enhanced features. - Verified enhanced features and method availability in the new system.aa2c910
-
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.
5a412ce
-
feat: add text cleaning functionality for TTS service to enhance input processing
3fde6b6 -
feat: update device selection in Wave2Vec2Inference to support GPU usage and enhance performance
fix: refine Vietnamese handoff rules in prompt.py for clearer user guidance1ea1cfa -
fix: reorganize import statements for clarity and remove unused imports
1f79c2f -
feat: refactor Wav2Vec2 character ASR to support quantization and improve model loading
c5ca6dc
-
feat: implement Wav2Vec2 character-level ASR with ONNX and Transformers support, add phoneme comparison and feedback generation
cef1d4a -
fix: update import statement for BaseModel in agent.py and add timing logs in speaking_controller.py
1a5420f -
Add Wav2Vec2 model conversion and inference to ONNX format
- Implemented Wav2Vec2ONNXConverter class for converting Wav2Vec2 models to ONNX format, including model loading, conversion, and verification. - Added Wav2Vec2ONNXInference class for performing inference using the converted ONNX model. - Included methods for softmax calculation and transcription of audio files. - Added utility functions for creating compatible models and exporting with fallback options for different ONNX opset versions. - Introduced optimization function for ONNX models. - Created helper function to convert numpy types to native Python types for better compatibility.df380ff -
Implement code changes to enhance functionality and improve performance
c6480d4 -
Implement feature X to enhance user experience and fix bug Y in module Z
dd47219
-
feat: add nltk to requirements for natural language processing
9c76eb3 -
feat: install ffmpeg in Dockerfile
c9e4c92 -
chore: remove compiled Python bytecode file
3d51c2e -
feat: add speaking route for pronunciation assessment API
64c08d9
-
update: evaluation
6020910
-
feat: set Teaching Agent as default and enhance interaction prompts
ce33d09 -
feat: evaluation when end
61e4b1e
-
feat: text to speech for AI response
7f15e1c
-
prompt: at handoff trigger for guiding agent roleplay
f8b4e8e -
prompt: hallucination at repsonse length
438e19d -
update prompt
cba740c -
prompt: add markdown and agent name
dcfb575 -
prompt: optimize
a546147 -
feat: audio v2 multi agent
20c3a0e
-
remove conversation management
4909ef6 -
Add trim_history function and update lesson chat route to handle text and audio inputs
a4cb278 -
Refactor roleplay agent implementation and update session handling for improved message processing
c0827a3
-
Enhance roleplay API to support audio messages and add comprehensive test cases
b7a3e32
-
Add lesson management functionality with JSON data integration and response models
0f1954e -
Implement lesson practice agent and related functionality
c0a7f25
-
update follow-up questions in scenarios for clarity and relevance
8bbe583
-
update prompt new tối nay
25ff07d -
update prompt claude
e61cbae -
first commit
7197de5 -
deployment: update
b9b869f -
Update Dockerfile
Verified signature477d59f -
Upload 74 files
Verified signature6cbca40
-
Update Dockerfile
Verified signatured976edd
-
Update app.py
Verified signature2d7b420 -
Update Dockerfile
Verified signature7189a67
-
Update app.py
Verified signature3485015 -
Update Dockerfile
Verified signature8257fba -
Update Dockerfile
Verified signature3c537af -
Update app.py
Verified signatureea1e28c