Codesota · Models · Google USMGoogle2 results · 1 benchmarks
Model card

Google USM.

Googleproprietary2B paramsConformer encoder + RNN-T/CTC

Universal Speech Model. Pretrained on 12M hours unlabeled + 28M hours supervised. 100+ languages.

§ 02 · Benchmarks

Every benchmark Google USM has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01LibriSpeechSpeech · Speech Recognitionwer-test-other4.1%#6/92023-03-02source ↗
02LibriSpeechSpeech · Speech Recognitionwer-test-clean2.0%#8/102023-03-02source ↗
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 Google USM actually performs.

Speech
1
benchmark
avg rank #7.0
§ 04 · Papers

1 paper with results for Google USM.

  1. 2023-03-02· Speech· 2 results

    Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages

§ 05 · Related models

Other Google models scored on Codesota.

Gemini 2.5 Pro
16 results · 2 SOTA
Gemini-3.1-Pro
7 results · 2 SOTA
Gemini 1.5 Pro
15 results · 1 SOTA
Gemini 3 Pro
Undisclosed params · 12 results · 1 SOTA
ViT-H/14
632M params · 2 results · 1 SOTA
CoCa (finetuned)
2.1B params · 1 result · 1 SOTA
Gemini 2.0 Flash
1 result · 1 SOTA
Noise2Music
Unknown params · 1 result · 1 SOTA
§ 06 · Sources & freshness

Where these numbers come from.

arxiv
2
results
2 of 2 rows marked verified.