# Automatic Speech Recognition on National Speech Corpus (NSC) English

Source: [Automatic Speech Recognition on National Speech Corpus (NSC) English](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-national-speech-corpus-nsc-english>)

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

Data updated: 2026-03-18T08:16:46.444Z

Evaluation of Automatic Speech Recognition performance on the National Speech Corpus (NSC) English dataset, measured using 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) | National Speech Corpus (NSC) English |
| Metric | WER |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 9 of 9 |
| 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-national-speech-corpus-nsc-english.md?metric=WER>): Lower is better; unit: PERCENT.

## Recorded results

| Method | WER | Result date | Report paper |
| --- | --- | --- | --- |
| MERaLiON-2-10B-ASR | 4.62 | Not recorded | 69ba31ad0636e5bf4afc09f7 |
| Polyglot-Lion-1.7B | 5.28 | Not recorded | 69ba31ad0636e5bf4afc09f7 |
| Polyglot-Lion-0.6B | 6.09 | Not recorded | 69ba31ad0636e5bf4afc09f7 |
| Qwen3-ASR-1.7B | 6.22 | Not recorded | 69ba31ad0636e5bf4afc09f7 |
| Qwen3-ASR-0.6B | 7.64 | Not recorded | 69ba31ad0636e5bf4afc09f7 |
| SeaLLMs-Audio-7B | 9.53 | Not recorded | 69ba31ad0636e5bf4afc09f7 |
| Qwen2.5-Omni-7B | 22.96 | Not recorded | 69ba31ad0636e5bf4afc09f7 |
| Whisper-large-v3-turbo | 32.02 | Not recorded | 69ba31ad0636e5bf4afc09f7 |
| Qwen2.5-Omni-3B | 34.79 | Not recorded | 69ba31ad0636e5bf4afc09f7 |

### MERaLiON-2-10B-ASR

WER: 4.62. Result ID: 69ba5f6e47f34ce924a4275b.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ad0636e5bf4afc09f7.md>)

Recorded evaluation configuration: {"Params":"10B"}. This record does not assert independent reproduction.

### Polyglot-Lion-1.7B

WER: 5.28. Result ID: 69ba5f6e47f34ce924a4275d.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ad0636e5bf4afc09f7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba31ad0636e5bf4afc09f7.md>)

[Implementation](<https://github.com/knoveleng/polyglot-lion>)

Recorded evaluation configuration: {"Params":"1.7B"}. This record does not assert independent reproduction.

### Polyglot-Lion-0.6B

WER: 6.09. Result ID: 69ba5f6e47f34ce924a4275c.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ad0636e5bf4afc09f7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba31ad0636e5bf4afc09f7.md>)

[Implementation](<https://github.com/knoveleng/polyglot-lion>)

Recorded evaluation configuration: {"Params":"0.6B"}. This record does not assert independent reproduction.

### Qwen3-ASR-1.7B

WER: 6.22. Result ID: 69ba5f6e47f34ce924a4275a.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ad0636e5bf4afc09f7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/697c3afda8b01e76cc8da424.md>)

Recorded evaluation configuration: {"Params":"1.7B"}. This record does not assert independent reproduction.

### Qwen3-ASR-0.6B

WER: 7.64. Result ID: 69ba5f6e47f34ce924a42759.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ad0636e5bf4afc09f7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/697c3afda8b01e76cc8da424.md>)

Recorded evaluation configuration: {"Params":"0.6B"}. This record does not assert independent reproduction.

### SeaLLMs-Audio-7B

WER: 9.53. Result ID: 69ba5f6e47f34ce924a42756.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ad0636e5bf4afc09f7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/690988893ef7ccd74e5e5d3b.md>)

Recorded evaluation configuration: {"Params":"7B"}. This record does not assert independent reproduction.

### Qwen2.5-Omni-7B

WER: 22.96. Result ID: 69ba5f6e47f34ce924a42758.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ad0636e5bf4afc09f7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77a21e209131cea7482c.md>)

Recorded evaluation configuration: {"Params":"7B"}. This record does not assert independent reproduction.

### Whisper-large-v3-turbo

WER: 32.02. Result ID: 69ba5f6e47f34ce924a42755.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ad0636e5bf4afc09f7.md>)

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

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

Recorded evaluation configuration: {"Params":"0.8B"}. This record does not assert independent reproduction.

### Qwen2.5-Omni-3B

WER: 34.79. Result ID: 69ba5f6e47f34ce924a42757.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ad0636e5bf4afc09f7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77a21e209131cea7482c.md>)

Recorded evaluation configuration: {"Params":"3B"}. This record does not assert independent reproduction.

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