speech to text benchmark
CoVoST2 en-zh
CoVoST 2 English-to-Chinese subset is part of the large-scale multilingual speech translation corpus derived from Common Voice. This subset focuses specifically on English to Chinese speech translation tasks within the broader CoVoST 2 dataset.
Updated Aug 7, 2026
Published models1
Registry coverage1
MetricScore
EvidenceB
CoVoST2 en-zh leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 0.414 points | 100.0% | 1 | C |
CoVoST2 en-zh highlights
The top published results on this benchmark's own scale.
What is CoVoST2 en-zh?
Definition and scoring fields from the benchmark registry.
CoVoST 2 English-to-Chinese subset is part of the large-scale multilingual speech translation corpus derived from Common Voice. This subset focuses specifically on English to Chinese speech translation tasks within the broader CoVoST 2 dataset.
Scores are shown in points. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- CoVoST2 en-zh
- Modality
- audio
- Primary category
- speech to text
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- covost2-en-zh|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about CoVoST2 en-zh.
Which model scores highest on CoVoST2 en-zh?
Qwen2.5-Omni-7B is currently ranked first with 0.414 points.
What does CoVoST2 en-zh measure?
CoVoST 2 English-to-Chinese subset is part of the large-scale multilingual speech translation corpus derived from Common Voice. This subset focuses specifically on English to Chinese speech translation tasks within the broader CoVoST 2 dataset.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.