Skip to content
View sinarashidi's full-sized avatar

Block or report sinarashidi

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
sinarashidi/README.md

Sina Rashidi

NLP & Speech Processing Researcher  ·  Research Assistant @ Columbia University  ·  M.Sc. Sharif University of Technology


About Me

I'm an AI researcher specializing in Natural Language Processing, Speech Processing, and Healthcare AI. Currently, I work as a Research Assistant at Columbia University under Prof. Maryam Zolnoori, where my research focuses on cognitive impairment detection from speech, text, and EHR data using multimodal deep learning and clinical NLP.

My work sits at the intersection of speech AI, multimodal modeling, and responsible clinical AI — with a strong emphasis on data-efficient learning, fairness, and explainability.


💼 Experience Highlights

  • Research Assistant — Columbia University (Jan 2024 – Present) · Cognitive AI from speech, multimodal Transformer pipelines, LoRA fine-tuning of Audio-LLMs
  • Deep Learning Research Engineer — BlueDopamine (Feb 2025 – Present) · LLM-based protein analysis, generative design, structure prediction
  • ML Engineer (Speech & NLP) — Sharif Information Systems & Data Science Center (Jan 2022 – Jan 2024) · RAG-based enterprise chatbot, SOTA ASR/TTS for Persian
  • Research Assistant — Sharif University of Technology (Jan 2021 – Jun 2024) · ASR, TTS, Voice Conversion, S2ST

🛠️ Tech Stack

Languages: Python · C++ · C · JavaScript · TypeScript

ML/DL: PyTorch · TensorFlow · Keras · HuggingFace Transformers · MLflow · Gradio · Scikit-learn

NLP/Speech: LangChain · FAISS

Data & Viz: NumPy · Pandas · Matplotlib

Tools: Linux · Docker · Git · LaTeX


🌐 sinarashidi.github.io

Pinned Loading

  1. phi4-speech-ad-detection phi4-speech-ad-detection Public

    Speech-based Alzheimer's detection via fine-tuned Phi-4 Multimodal. Audio + transcription, LoRA, single-GPU training.

    Python

  2. SpeechCARE/SpeechCura SpeechCARE/SpeechCura Public

    A framework for speech data augmentation for healthcare applications

    Python

  3. S2ST-Transformer S2ST-Transformer Public

    Direct Speech-to-Speech Translation using a unit-based Transformer model with a pre-trained Conformer encoder

    Jupyter Notebook 2

  4. llama-2-persian llama-2-persian Public

    Fine-tuning code for LLaMA-2 for Persian language

    Jupyter Notebook 10 2