# Automatic Speech Recognition on L2-ARCTIC (test)

Source: [Automatic Speech Recognition on L2-ARCTIC (test)](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-l2-arctic-test>)

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

Data updated: 2026-03-09T07:33:15.276Z

Evaluation of Automatic Speech Recognition performance on the test split of the L2-ARCTIC corpus, reporting Word Error Rate (WER) and Delta 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) | L2-ARCTIC (test) |
| 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-l2-arctic-test.md?metric=WER>): Lower is better; unit: PERCENT.

- [Delta WER](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-l2-arctic-test.md?metric=Delta%20WER>): Lower is better; unit: PERCENT.

## Recorded results

| Method | WER | Result date | Report paper |
| --- | --- | --- | --- |
| PEFT | 7.2 | Not recorded | 69ae53fd2d603e6de3e42afc |
| PEFT | 7.82 | Not recorded | 69ae53fd2d603e6de3e42afc |
| PEFT | 8.61 | Not recorded | 69ae53fd2d603e6de3e42afc |
| Mean Shift Steering | 9.39 | Not recorded | 69ae53fd2d603e6de3e42afc |
| Mean Shift Steering | 10.07 | Not recorded | 69ae53fd2d603e6de3e42afc |
| Mean Shift Steering | 10.22 | Not recorded | 69ae53fd2d603e6de3e42afc |
| Base Model | 14.26 | Not recorded | 69ae53fd2d603e6de3e42afc |
| Base Model | 15.31 | Not recorded | 69ae53fd2d603e6de3e42afc |
| Base Model | 18.13 | Not recorded | 69ae53fd2d603e6de3e42afc |

### PEFT

WER: 7.2. Result ID: 69ae77ad6dbb7075b9563d25.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53fd2d603e6de3e42afc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65e31e209131cea0d324.md>)

[Implementation](<https://github.com/google-research/adapter-bert>)

Recorded evaluation configuration: {"Accent":"Arabic","Number of training samples":"802"}. This record does not assert independent reproduction.

### PEFT

WER: 7.82. Result ID: 69ae77ad6dbb7075b9563d28.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53fd2d603e6de3e42afc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65e31e209131cea0d324.md>)

[Implementation](<https://github.com/google-research/adapter-bert>)

Recorded evaluation configuration: {"Accent":"Hindi","Number of training samples":"790"}. This record does not assert independent reproduction.

### PEFT

WER: 8.61. Result ID: 69ae77ad6dbb7075b9563d2b.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53fd2d603e6de3e42afc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65e31e209131cea0d324.md>)

[Implementation](<https://github.com/google-research/adapter-bert>)

Recorded evaluation configuration: {"Accent":"Spanish","Number of training samples":"796"}. This record does not assert independent reproduction.

### Mean Shift Steering

WER: 9.39. Result ID: 69ae77ad6dbb7075b9563d2a.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53fd2d603e6de3e42afc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ae53fd2d603e6de3e42afc.md>)

Recorded evaluation configuration: {"Accent":"Spanish","Number of training samples":"796"}. This record does not assert independent reproduction.

### Mean Shift Steering

WER: 10.07. Result ID: 69ae77ad6dbb7075b9563d24.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53fd2d603e6de3e42afc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ae53fd2d603e6de3e42afc.md>)

Recorded evaluation configuration: {"Accent":"Arabic","Number of training samples":"802"}. This record does not assert independent reproduction.

### Mean Shift Steering

WER: 10.22. Result ID: 69ae77ad6dbb7075b9563d27.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53fd2d603e6de3e42afc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ae53fd2d603e6de3e42afc.md>)

Recorded evaluation configuration: {"Accent":"Hindi","Number of training samples":"790"}. This record does not assert independent reproduction.

### Base Model

WER: 14.26. Result ID: 69ae77ad6dbb7075b9563d26.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53fd2d603e6de3e42afc.md>)

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

Recorded evaluation configuration: {"Accent":"Hindi","Number of training samples":"790"}. This record does not assert independent reproduction.

### Base Model

WER: 15.31. Result ID: 69ae77ad6dbb7075b9563d29.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53fd2d603e6de3e42afc.md>)

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

Recorded evaluation configuration: {"Accent":"Spanish","Number of training samples":"796"}. This record does not assert independent reproduction.

### Base Model

WER: 18.13. Result ID: 69ae77ad6dbb7075b9563d23.

[Reporting paper](<https://www.sota2.com/research/paper/69ae53fd2d603e6de3e42afc.md>)

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

Recorded evaluation configuration: {"Accent":"Arabic","Number of training samples":"802"}. This record does not assert independent reproduction.

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