Spaces:
Sleeping
Sleeping
Commit History
-
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 -
Update Dockerfile
Verified signaturecacee39 -
Update app.py
Verified signatureda404fd -
Update app.py
Verified signaturee7c0eb0 -
Update app.py
Verified signature072178c -
Update app.py
Verified signature0f90aa0 -
Update Dockerfile
Verified signaturec52a700 -
Update app.py
Verified signature409ca74