# Automatic Speech Recognition on MuST-C En-De COMMON (test)

Source: [Automatic Speech Recognition on MuST-C En-De COMMON (test)](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-must-c-en-de-common-test>)

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

Data updated: 2026-02-26T06:08:28.978Z

Evaluation of Automatic Speech Recognition performance on the English-to-German common test split of the MuST-C dataset, measured by Word Error Rate (WER).

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 | Automatic Speech Recognition |
| Dataset (including any stated split) | MuST-C En-De COMMON (test) |
| Metric | WER |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 16 of 16 |
| 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

- [WER](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-must-c-en-de-common-test.md?metric=WER>): Lower is better; unit: PERCENT.

## Recorded results

| Method | WER | Result date | Report paper |
| --- | --- | --- | --- |
| Specialized | 6.54 | Not recorded | 68fa79061e209131cea7bc25 |
| contr-cos-all + giga | 9.31 | Not recorded | 68fa79061e209131cea7bc25 |
| Cascaded | 9.9 | Not recorded | 68fa6c141e209131cea32028 |
| contr-cos-all + asr + giga | 10.03 | Not recorded | 68fa79061e209131cea7bc25 |
| contr-cos-all + asr | 10.04 | Not recorded | 68fa79061e209131cea7bc25 |
| ASR pretrain | 10.28 | Not recorded | 68fa79061e209131cea7bc25 |
| contr-cos-all + giga | 10.94 | Not recorded | 68fa79061e209131cea7bc25 |
| contr-cos-all + asr + giga | 11.12 | Not recorded | 68fa79061e209131cea7bc25 |
| ASR pretrain + giga | 11.48 | Not recorded | 68fa79061e209131cea7bc25 |
| contr-cos-all + asr | 11.68 | Not recorded | 68fa79061e209131cea7bc25 |
| Qwen2-Audio-7b | 12.03 | Not recorded | 68fa79061e209131cea7bc25 |
| ASR pretrain + giga | 12.16 | Not recorded | 68fa79061e209131cea7bc25 |
| ASR pretrain | 12.21 | Not recorded | 68fa79061e209131cea7bc25 |
| contr-cos-all | 12.56 | Not recorded | 68fa79061e209131cea7bc25 |
| contr-cos-all | 13.06 | Not recorded | 68fa79061e209131cea7bc25 |
| BLSP-1slm-7b | 44.51 | Not recorded | 68fa79061e209131cea7bc25 |

### Specialized

WER: 6.54. Result ID: 6995b9443badfaffe6ba6cad.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc25.md>)

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

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

Recorded evaluation configuration: {"FT Data":"N/A"}. This record does not assert independent reproduction.

### contr-cos-all + giga

WER: 9.31. Result ID: 6995b9443badfaffe6ba6cb9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc25.md>)

[Implementation](<https://github.com/MaikeZuefle/contr-pretraining>)

Recorded evaluation configuration: {"FT Data":"100%"}. This record does not assert independent reproduction.

### Cascaded

WER: 9.9. Result ID: 698ecb54ffc3901de0a144e2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c141e209131cea32028.md>)

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

### contr-cos-all + asr + giga

WER: 10.03. Result ID: 6995b9443badfaffe6ba6cbb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc25.md>)

[Implementation](<https://github.com/MaikeZuefle/contr-pretraining>)

Recorded evaluation configuration: {"FT Data":"100%"}. This record does not assert independent reproduction.

### contr-cos-all + asr

WER: 10.04. Result ID: 6995b9443badfaffe6ba6cba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc25.md>)

[Implementation](<https://github.com/MaikeZuefle/contr-pretraining>)

Recorded evaluation configuration: {"FT Data":"100%"}. This record does not assert independent reproduction.

### ASR pretrain

WER: 10.28. Result ID: 6995b9443badfaffe6ba6cb6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72d71e209131cea58d8a.md>)

Recorded evaluation configuration: {"FT Data":"100%"}. This record does not assert independent reproduction.

### contr-cos-all + giga

WER: 10.94. Result ID: 6995b9443badfaffe6ba6cb3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc25.md>)

[Implementation](<https://github.com/MaikeZuefle/contr-pretraining>)

Recorded evaluation configuration: {"FT Data":"10%"}. This record does not assert independent reproduction.

### contr-cos-all + asr + giga

WER: 11.12. Result ID: 6995b9443badfaffe6ba6cb5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc25.md>)

[Implementation](<https://github.com/MaikeZuefle/contr-pretraining>)

Recorded evaluation configuration: {"FT Data":"10%"}. This record does not assert independent reproduction.

### ASR pretrain + giga

WER: 11.48. Result ID: 6995b9443badfaffe6ba6cb7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78571e209131cea77d1e.md>)

[Implementation](<https://github.com/SpeechColab/GigaSpeech>)

Recorded evaluation configuration: {"FT Data":"100%"}. This record does not assert independent reproduction.

### contr-cos-all + asr

WER: 11.68. Result ID: 6995b9443badfaffe6ba6cb4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc25.md>)

[Implementation](<https://github.com/MaikeZuefle/contr-pretraining>)

Recorded evaluation configuration: {"FT Data":"10%"}. This record does not assert independent reproduction.

### Qwen2-Audio-7b

WER: 12.03. Result ID: 6995b9443badfaffe6ba6caf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6017e.md>)

Recorded evaluation configuration: {"FT Data":"N/A"}. This record does not assert independent reproduction.

### ASR pretrain + giga

WER: 12.16. Result ID: 6995b9443badfaffe6ba6cb1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78571e209131cea77d1e.md>)

[Implementation](<https://github.com/SpeechColab/GigaSpeech>)

Recorded evaluation configuration: {"FT Data":"10%"}. This record does not assert independent reproduction.

### ASR pretrain

WER: 12.21. Result ID: 6995b9443badfaffe6ba6cb0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72d71e209131cea58d8a.md>)

Recorded evaluation configuration: {"FT Data":"10%"}. This record does not assert independent reproduction.

### contr-cos-all

WER: 12.56. Result ID: 6995b9443badfaffe6ba6cb8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc25.md>)

[Implementation](<https://github.com/MaikeZuefle/contr-pretraining>)

Recorded evaluation configuration: {"FT Data":"100%"}. This record does not assert independent reproduction.

### contr-cos-all

WER: 13.06. Result ID: 6995b9443badfaffe6ba6cb2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc25.md>)

[Implementation](<https://github.com/MaikeZuefle/contr-pretraining>)

Recorded evaluation configuration: {"FT Data":"10%"}. This record does not assert independent reproduction.

### BLSP-1slm-7b

WER: 44.51. Result ID: 6995b9443badfaffe6ba6cae.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73681e209131cea5c491.md>)

Recorded evaluation configuration: {"FT Data":"N/A"}. This record does not assert independent reproduction.

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