Model card
Granite Speech 3.3 8B.
IBMopen-source8B paramsTransformer
§ 02 · Benchmarks
Every benchmark Granite Speech 3.3 8B has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | LibriSpeech | Speech · Speech Recognition | wer | 2.9% | #21 | — | source ↗ |
| 02 | SPGISpeech | Speech · Speech Recognition | wer | 3.9% | #25 | — | source ↗ |
| 03 | TED-LIUM | Speech · Speech Recognition | wer | 3.4% | #43 | — | source ↗ |
| 04 | VoxPopuli | Speech · Speech Recognition | wer | 5.7% | #51 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area
Where Granite Speech 3.3 8B actually performs.
§ 04 · Papers
1 paper with results for Granite Speech 3.3 8B.
- 2025-05-13· 4 results
Granite-speech: open-source speech-aware LLMs with strong English ASR capabilities
§ 05 · Related models
Other IBM models scored on Codesota.
§ 06 · Sources & freshness
Where these numbers come from.
pwc-dump
4
results
0 of 4 rows marked verified.