Model card
Granite Speech 4.1 2B.
IBMopen-source2B paramsTransformer (speech+text)
§ 02 · Benchmarks
Every benchmark Granite Speech 4.1 2B has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | LibriSpeech | Speech · Speech Recognition | wer | 1.3% | #2 | — | source ↗ |
| 02 | SPGISpeech | Speech · Speech Recognition | wer | 3.8% | #32 | — | source ↗ |
| 03 | Open ASR Leaderboard | Speech · Speech Recognition | rtfx | 231.29 | #34 | — | source ↗ |
| 04 | GigaSpeech | Speech · Speech Recognition | wer | 9.8% | #43 | — | source ↗ |
| 05 | TED-LIUM | Speech · Speech Recognition | wer | 3.1% | #45 | — | source ↗ |
| 06 | AMI-IHM | Speech · Speech Recognition | wer | 8.1% | #50 | — | source ↗ |
| 07 | Earnings-22 | Speech · Speech Recognition | wer | 8.4% | #50 | — | source ↗ |
| 08 | Open ASR Leaderboard | Speech · Speech Recognition | wer | 5.3% | #52 | — | source ↗ |
| 09 | VoxPopuli | Speech · Speech Recognition | wer | 5.7% | #52 | — | 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 4.1 2B actually performs.
§ 04 · Papers
1 paper with results for Granite Speech 4.1 2B.
- 2025-05-13· 9 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
9
results
0 of 9 rows marked verified.