Zhifu Gao
高级算法工程师 at 阿里巴巴集团达摩院
Hefei, Anhui, China
Summary
🤩
Rockstar🎓
Top SchoolZhifu Gao is a senior algorithm engineer with nine years of experience specializing in speech recognition and ML engineering, currently working at Alibaba DAMO Academy in Hefei. He has contributed to prominent open-source projects like ModelScope and FunASR, driving ASR pipeline integration, platform adaptation (including macOS), and updates to keep toolkits aligned with state-of-the-art models. His work spans practical inference engineering—batch padding, long-input support, and parameter-passing bug fixes—bridging research-quality models to production-ready pipelines. Trained with a master's from the University of Science and Technology of China, he combines deep technical rigor with hands-on system integration experience, often tackling the less visible but critical engineering details that make speech models robust in real-world deployments.
9 years of coding experience
Anhui UniversityMaster's degree, Master's degree at University of Science and Technology of China
Github Skills (10)
pytorch10
machine-learning10
speech-recognition10
audio-processing10
nlp10
pipelining10
python10
pipe10
pipeline10
deep-learning9
Programming languages (4)
Github contributions (5)
modelscope/FunASR
Nov 2022 - Mar 2023
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
Role in this project:
ML Engineer
ML EngineerContributions:3 releases, 330 reviews, 361 commits in 3 months
Contributions summary:Zhifu's commits primarily involve modifications and additions to the `funasr` project, which is a speech recognition toolkit. The changes involve adapting the paraformer model, including batch padding, and long input support. The commits also show work on integrating the model with Modelscope and include modifications to pre-existing inference scripts and configuration files.
asrctcspeech-recognitionspeaker-verificationpunctuation
modelscope/modelscope
Jan 2023 - May 2024
ModelScope: bring the notion of Model-as-a-Service to life.
Role in this project:ML Engineer
ML EngineerContributions:5 reviews, 12 PRs, 11 pushes in 1 year 3 months
Contributions summary:Zhifu primarily contributed to the integration and maintenance of Automatic Speech Recognition (ASR) pipelines within the ModelScope framework, specifically focusing on the integration of funasr. The contributions include supporting funasr for different platforms like macOS, modifying pipeline parameters, and removing legacy easyasr dependency, also fixing bugs related to model parameter passing. Additionally, the user updated funasr to version 1.0, indicating efforts to keep the project up-to-date with the latest advancements in speech recognition technology.
nlppytorchmulti-modalpythonscience
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.