quic/efficient-transformers
Feb 2025 – Feb 2025
1 Month active
Languages Used
Python
Technical Skills
Cloud AI 100Deep LearningFull Stack DevelopmentMachine LearningModel OptimizationONNX
kdulla
PROFILE
Kdulla
Kiran Dulla integrated OpenAI’s Whisper model into the quic/efficient-transformers repository, enabling its compilation and execution on Cloud AI 100 hardware. This work involved adapting the QEfficient pipeline to support Whisper’s architecture, updating model handling, export, and generation paths to address Whisper-specific requirements, and laying the foundation for broader OpenAI model compatibility. Using Python and leveraging skills in deep learning, ONNX, and model optimization, Kiran ensured that Whisper-based speech recognition could be deployed efficiently and at scale. The depth of the integration reflects a strong understanding of both full stack development and the nuances of transformer-based model deployment.
Overall Statistics
Feature vs Bugs
100%Features
Repository Contributions
1Total
Bugs
0
Commits
1
Features
1
Lines of code
1,851
Activity Months1
Your Network
38 peopleShared Repositories
38
Abukhoyer ShaikMember
Amit RajMember
Anuj GuptaMember
asmigoswMember
Dhiraj Kumar SahMember
Dipankar SarkarMember
Hem AgnihotriMember
Meet PatelMember
Swati AllabadiMember
Work History
February 2025
1 Commits • 1 Features
Feb 1, 2025February 2025: Delivered Whisper model support in QEfficient and prepared the pipeline for Whisper-based inference on Cloud AI 100, enhancing model coverage and deployment scalability. This work includes integration of Whisper architecture into QEfficient, updates to handling, export, and generation to accommodate Whisper-specific requirements, and groundwork for broader OpenAI model compatibility.
1 Commits • 1 Features
Feb 1, 2025February 2025: Delivered Whisper model support in QEfficient and prepared the pipeline for Whisper-based inference on Cloud AI 100, enhancing model coverage and deployment scalability. This work includes integration of Whisper architecture into QEfficient, updates to handling, export, and generation to accommodate Whisper-specific requirements, and groundwork for broader OpenAI model compatibility.
February 2025
Activity
Loading activity data...
Quality Metrics
Correctness90.0%
Maintainability80.0%
Architecture90.0%
Performance80.0%
AI Usage60.0%
Skills & Technologies
Programming Languages
Python
Technical Skills
Cloud AI 100Deep LearningFull Stack DevelopmentMachine LearningModel OptimizationONNXSpeech RecognitionTransformers
Repositories Contributed To
Overview of all repositories you've contributed to across your timeline