Technical Blog

Building Multimodal AI Pipelines With BERT, BART and Whisper

March 19, 2026

Introduction

Multimodal AI is no longer a research curiosity—it's a practical necessity. Modern applications often need to process a mix of text, audio, images, and video. In this post, I'll walk through building a production‑grade multimodal pipeline that combines Whisper (for speech‑to‑text), BERT (for understanding and classification), and BART (for summarization and generation).

The use case: a system that ingests audio recordings (meetings, lectures, calls), transcribes them with Whisper, extracts key insights using BERT‑based NER and classification, and then generates concise summaries and action items with BART. All in near‑real‑time.

Pipeline Overview

The pipeline is a directed flow with three main stages:

All stages are orchestrated using a task queue (Celery) and can be scaled independently based on workload.

Whisper: Speech-to-Text Foundation

We use OpenAI Whisper (the large‑v3 model) for transcription. It handles multiple languages and noisy audio well. In production, we use the faster‑whisper implementation for a ~4x speedup with minimal accuracy loss.

Key considerations:

In our tests, Whisper achieved a Word Error Rate (WER) of 5.2% on clean speech and 8.7% on recorded meetings with moderate background noise.

BERT: Understanding the Text

For understanding, we fine‑tuned a BERT‑base model for three tasks:

We used a single multi‑task BERT model with multiple classification heads, sharing the encoder. This reduced memory footprint and improved inference speed.

We also added a key‑phrase extraction module using a combination of BERT embeddings and RAKE (Rapid Automatic Keyword Extraction) to highlight important terms.

BART: Summarization and Generation

BART (BART‑large) is our workhorse for generation. We use it for two purposes:

We fine‑tuned BART on a custom dataset of meeting transcripts and summaries (about 5,000 examples) to improve coherence and style. The fine‑tuned model achieved a ROUGE‑L score of 0.41 on our held‑out test set, a 12% improvement over the base model.

For action items, we used a prompt‑based approach: we prepend the transcript with "Extract action items from the following conversation:" and let BART generate a bulleted list. We then post‑process to deduplicate and clean.

Architecture and Orchestration

Audio InputMP3 · WAV · streaming
Whisper (STT)Transcription · diarization
BERT (Understanding)NER · Intent · Sentiment
BART (Generation)Summarization · action items
OutputJSON · markdown · dashboard
Audio → Text → Entities → Summary → Actions

We deploy the pipeline as a set of microservices using FastAPI for REST endpoints and WebSockets for streaming audio. Each model runs in its own container with a GPU assigned based on its needs (Whisper and BERT share a GPU, BART has its own for heavy generation).

Orchestration is handled by Celery with Redis as the broker. We have separate queues for each stage, allowing us to scale the summarization workers independently during peak load.

Performance Optimizations

To meet near‑real‑time requirements, we applied several optimizations:

After optimizations, our end‑to‑end latency for a 5‑minute audio segment dropped from 18 seconds to 6 seconds (p95), making it suitable for interactive use.

Evaluation and Metrics

We evaluate each component separately and the pipeline as a whole:

We also track business metrics: user satisfaction score (from feedback widget), average time to summary, and cost per audio minute (currently ~$0.002/min).

Lessons Learned

Building a multimodal pipeline is a systems engineering challenge. Here are our key takeaways:

Conclusion

Multimodal AI is becoming essential for modern applications. By combining Whisper, BERT, and BART in a thoughtful pipeline, we built a system that transcribes, understands, and summarizes audio content with near‑real‑time performance. The modular architecture allows us to swap components (e.g., replace Whisper with a custom STT) as better models emerge.

The journey from a Jupyter prototype to a production pipeline involved careful model selection, performance tuning, and rigorous evaluation. But the result is a system that delivers real value—saving meeting participants time and helping teams stay aligned.

I'd love to hear about your own multimodal projects. Reach out on Twitter or GitHub.