Recent studyBlind TTS Elo is live. Compare two anonymous voice samples, vote after listening, and help separate real preference signal from noise.Vote in the study ->
Codesota · Models · Granite Speech 3.3 2B9 results · 8 benchmarks
Model card

Granite Speech 3.3 2B.

unknown
§ 02 · Benchmarks

Every benchmark Granite Speech 3.3 2B has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01SPGISpeechSpeech · Speech Recognitionwer3.9%#27/56source ↗
02GigaSpeechSpeech · Speech Recognitionwer10.7%#30/47source ↗
03Open ASR LeaderboardSpeech · Speech Recognitionrtfx270.57#31/50source ↗
04LibriSpeechSpeech · Speech Recognitionwer3.3%#32/92source ↗
05TED-LIUMSpeech · Speech Recognitionwer3.6%#40/50source ↗
06Earnings-22Speech · Speech Recognitionwer10.3%#47/50source ↗
07AMI-IHMSpeech · Speech Recognitionwer8.9%#48/50source ↗
08Open ASR LeaderboardSpeech · Speech Recognitionwer6.0%#48/52source ↗
09VoxPopuliSpeech · Speech Recognitionwer5.9%#49/55source ↗
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 2B actually performs.

Speech
8
benchmarks
avg rank #39.1
§ 04 · Papers

1 paper with results for Granite Speech 3.3 2B.

  1. 2025-05-13· 9 results

    Granite-speech: open-source speech-aware LLMs with strong English ASR capabilities

§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
9
results
0 of 9 rows marked verified.