# Speech-to-English Translation on CoVoST2 All X-en (test)

Source: [Speech-to-English Translation on CoVoST2 All X-en (test)](<https://www.sota2.com/research/sota/speech-to-english-translation-on-covost2-all-x-en-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:36:52.829Z

Evaluation of Speech-to-English Translation performance on the test split of the CoVoST2 dataset, specifically focusing on the 'All X-en' language direction setting.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Speech-to-English Translation |
| Dataset (including any stated split) | CoVoST2 All X-en (test) |
| Metric | BLEU |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [BLEU](<https://www.sota2.com/research/sota/speech-to-english-translation-on-covost2-all-x-en-test.md?metric=BLEU>): Higher is better; unit: PERCENT.

## Recorded results

| Method | BLEU | Result date | Report paper |
| --- | --- | --- | --- |
| Whisper | 29.1 | Not recorded | 68fa6e2c1e209131cea3e51b |
| Maestro | 25.2 | Not recorded | 68fa6e2c1e209131cea3e51b |
| mSLAM-CTC | 24.8 | Not recorded | 68fa6e2c1e209131cea3e51b |
| XLS-R | 22.1 | Not recorded | 68fa6e2c1e209131cea3e51b |
| XMEF-X | 14.7 | Not recorded | 68fa6e2c1e209131cea3e51b |

### Whisper

BLEU: 29.1. Result ID: 699013b33a6c314849fdf3b3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e2c1e209131cea3e51b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e2c1e209131cea3e51b.md>)

[Implementation](<https://github.com/openai/whisper>)

Recorded evaluation configuration: {"Evaluation protocol":"Zero-Shot"}. This record does not assert independent reproduction.

### Maestro

BLEU: 25.2. Result ID: 699013b33a6c314849fdf3b2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e2c1e209131cea3e51b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ce21e209131cea367a0.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### mSLAM-CTC

BLEU: 24.8. Result ID: 699013b33a6c314849fdf3b1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e2c1e209131cea3e51b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bb51e209131cea2fc19.md>)

Recorded evaluation configuration: {"Parameters":"2B"}. This record does not assert independent reproduction.

### XLS-R

BLEU: 22.1. Result ID: 699013b33a6c314849fdf3b0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e2c1e209131cea3e51b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b791e209131cea2e651.md>)

[Implementation](<https://www.sota2.com/www.github.com/pytorch/fairseq/tree/master/examples/wav2vec/xlsr>)

Recorded evaluation configuration: {"Parameters":"2B"}. This record does not assert independent reproduction.

### XMEF-X

BLEU: 14.7. Result ID: 699013b33a6c314849fdf3af.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e2c1e209131cea3e51b.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.