# Granite Speech 5.0 TurboCTC model notes: Voice Benchmark Profile

> IBM’s model card and Granite 4.2 blog document the model’s size, training data, and throughput; Open ASR leaderboard results are published as images.

- Scope: Parameter count, training hours, and RTFx throughput on a single H200
- Measurement lanes: Latency
- Primary metric: Throughput (higher is better)
- Available evidence: Throughput published in text; WER charts are images
- Owner: IBM
- Source snapshots refreshed: 2026-09-11

## Interpretation limit

IBM publishes the Open ASR and FFASR leaderboard comparisons only as images, so no WER value is transcribed here.

## Primary sources

- [Owner page](https://huggingface.co/ibm-granite/granite-speech-5.0-470m-turboctc)

Canonical page: https://benchlm.ai/voice-benchmarks/granite-speech-5-0-470m-turboctc-launch-evaluation