AWS Ships WhisperX Deep Learning Container: Word-Level Timestamps and Speaker Diarization on SageMaker
AWS ML Blog · rss · 2026-09-25
AWS ML Blog details deploying the WhisperX Deep Learning Container (DLC) on SageMaker AI, fixing two pain points of generic speech-to-text: utterance-level timestamps and no speaker labels.
- WhisperX capabilities: wraps OpenAI Whisper with batched inference, wav2vec2 forced alignment for per-word timestamps, and speaker diarization — suited to contact centers, meetings, media captioning (SRT/VTT), and compliance review.
- Deployment: the GPU-ready image bundles all weights, no Hugging Face token needed; supports real-time endpoints (short clips under the 60s cap) and asynchronous endpoints (long audio via S3, autoscale-to-zero for cost savings).
- Production details: you must pin the GPU AMI al2-ami-sagemaker-inference-gpu-3-1 or the container fails to start; instance choices are ml.g4dn.xlarge (cost) or ml.g5.2xlarge (headroom); scale throughput by adding instances, not concurrency. A runnable end-to-end notebook is available in the AWS Samples repo.
More from coding & agent
- Too many 'X times faster' claims hide extremely narrow benchmarks, says Ruff author — charliermarsh · 2026-09-25
- Ruff author Charlie Marsh: microbenchmark culture is getting worse — charliermarsh · 2026-09-25
- Claude API adds inline tool definitions for adding full tools mid-conversation — EricBuess · 2026-09-25
- Hands-on repo teaches GitHub stacked PRs with gh stack CLI and an AI coding agent workshop — DanWahlin · 2026-09-25
- Energy's AI agent can log in and pay for you, with credentials kept local and hidden from LLMs — emilahlback · 2026-09-25
- OpenRouter launches unified web search server tool with per-provider pricing — jeff_weinstein · 2026-09-25