Voice to Data: LLM Pipeline for Lab Notebooks

Python
LLM
NLP
MLOps
Lab Automation
A voice-driven pipeline that turns laboratory bench recordings into structured, validated records — ASR, LLM extraction, domain validation, and an audit-ready trail designed for regulated pharma and biotech R&D.
Published

February 22, 2026

Overview

Scientists in formulation, analytical, and cell culture labs spend 20–40 minutes per bench session transcribing observations into ELN/LIMS systems after the experiment, from memory, and under time pressure. This pipeline removes the keyboard from the critical path.

The pipeline takes an audio file recorded at the bench and produces a structured, validated JSON record ready for ELN/LIMS handoff, with an immutable audit trail designed to support traceability, review, and controlled handoff in regulated environments.

All processing runs locally: no audio or text leaves your network. In many regulated R&D settings, that deployment model materially simplifies security review, data handling, and validation.

Architecture

Voice (audio file)
     │
     ▼
┌──────────────────────────────┐
│  Stage 1 — ASR               │
│  faster-whisper (local)      │
└──────────────┬───────────────┘
               │
               ▼
┌──────────────────────────────┐
│  Stage 2 — Extraction        │
│  Instructor + Pydantic       │
│  + Ollama (local LLM)        │
└──────────────┬───────────────┘
               │
               ▼
┌──────────────────────────────┐
│  Stage 3 — Validation        │
│  DomainValidator             │
│  (plausibility + mandatory)  │
└──────────────┬───────────────┘
               │
               ▼
┌──────────────────────────────┐
│  Stage 4 — Serialization     │
│  JSON + AuditRecord          │
└──────────────────────────────┘

Stack

Layer Tool Rationale
ASR faster-whisper (CTranslate2) Open-weights, 2–4× faster than PyTorch Whisper, CPU-capable
LLM structured extraction instructor + ollama Guaranteed schema-conformant output via tool-calling — no JSON parsing brittleness
Schema & validation pydantic v2 Type enforcement + domain plausibility checks in one place
Dependency management uv Fast, reproducible, lockfile-based

Key design decisions

Why Instructor over raw LLM JSON? Asking an LLM to “return JSON” produces unreliable free-form output. Instructor uses the model’s tool-calling mode to force every field of the Pydantic schema to be explicitly populated. Missing fields become null rather than hallucinated values — which matters a great deal in a compliance context.

Two-tier validation: Pydantic enforces structural correctness (types, enums). A separate DomainValidator class enforces scientific plausibility (for example, pH values between 0 and 14, viscosity ranges, and unit whitelists). These are kept separate intentionally: structural failures are hard blocks; domain flags are soft and route the record to human review.

Hedged values as a first-class concept: When a scientist says “approximately 4,200 millipascal seconds”, the hedged=True flag is set in the schema and the record goes to the review queue — not committed blindly. This is a deliberate design choice, not a limitation.

Compliance notes

  • Audit trail: every record carries a SHA-256 hash of the raw transcript, model version strings, extraction timestamp, and review status to support record traceability and controlled review
  • Model version-locking: models are pinned; updates are treated as change control events requiring requalification
  • Temperature = 0: extraction calls are as deterministic as the model allows
  • Local-only: no cloud API calls, which simplifies deployment in environments with strict data-handling constraints
  • System scope: the pipeline covers record creation and traceability; a full 21 CFR Part 11 deployment would still depend on surrounding controls such as identity, signatures, retention, and SOPs
Back to top