# Automatic Speech Recognition on WAXAL (Full)

Source: [Automatic Speech Recognition on WAXAL (Full)](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-waxal-full>)

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

Data updated: 2026-06-02T13:27:49.410Z

Evaluation of Automatic Speech Recognition performance on the full WAXAL dataset, reporting language-specific results across multiple languages and the overall mean score.

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) | WAXAL (Full) |
| Metric | Amharic Performance |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [Amharic Performance](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-waxal-full.md?metric=Amharic%20Performance>): Higher is better; unit: SCALAR.

- [Acholi Performance](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-waxal-full.md?metric=Acholi%20Performance>): Higher is better; unit: SCALAR.

- [Akan Performance](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-waxal-full.md?metric=Akan%20Performance>): Higher is better; unit: SCALAR.

- [Dagaare Performance](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-waxal-full.md?metric=Dagaare%20Performance>): Higher is better; unit: SCALAR.

- [Dagbani Performance](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-waxal-full.md?metric=Dagbani%20Performance>): Higher is better; unit: SCALAR.

- [Ewe Performance](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-waxal-full.md?metric=Ewe%20Performance>): Higher is better; unit: SCALAR.

- [Fula Performance](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-waxal-full.md?metric=Fula%20Performance>): Higher is better; unit: SCALAR.

- [Ikposo Performance](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-waxal-full.md?metric=Ikposo%20Performance>): Higher is better; unit: SCALAR.

- [Lingala Performance](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-waxal-full.md?metric=Lingala%20Performance>): Higher is better; unit: SCALAR.

- [Luganda Performance](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-waxal-full.md?metric=Luganda%20Performance>): Higher is better; unit: SCALAR.

- [Malagasy Performance](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-waxal-full.md?metric=Malagasy%20Performance>): Higher is better; unit: SCALAR.

- [Masaaba Performance](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-waxal-full.md?metric=Masaaba%20Performance>): Higher is better; unit: SCALAR.

- [Nyankole Performance](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-waxal-full.md?metric=Nyankole%20Performance>): Higher is better; unit: SCALAR.

- [Oromo Performance](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-waxal-full.md?metric=Oromo%20Performance>): Higher is better; unit: SCALAR.

- [Shona Performance](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-waxal-full.md?metric=Shona%20Performance>): Higher is better; unit: SCALAR.

- [Sidama Performance](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-waxal-full.md?metric=Sidama%20Performance>): Higher is better; unit: SCALAR.

- [Soga Performance](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-waxal-full.md?metric=Soga%20Performance>): Higher is better; unit: SCALAR.

- [Tigrinya Performance](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-waxal-full.md?metric=Tigrinya%20Performance>): Higher is better; unit: SCALAR.

- [Wolaytta Performance](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-waxal-full.md?metric=Wolaytta%20Performance>): Higher is better; unit: SCALAR.

- [Mean Performance](<https://www.sota2.com/research/sota/automatic-speech-recognition-on-waxal-full.md?metric=Mean%20Performance>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Amharic Performance | Result date | Report paper |
| --- | --- | --- | --- |
| Whisper L | 254.3 | Not recorded | 6a1e6423dbd7150506f857d5 |
| MMS-1B | 100.7 | Not recorded | 6a1e6423dbd7150506f857d5 |
| Omni. | 51.1 | Not recorded | 6a1e6423dbd7150506f857d5 |
| Whisp. T | 41.3 | Not recorded | 6a1e6423dbd7150506f857d5 |
| MMS-300M | 37.8 | Not recorded | 6a1e6423dbd7150506f857d5 |
| Whisp. S | 33.6 | Not recorded | 6a1e6423dbd7150506f857d5 |

### Whisper L

Amharic Performance: 254.3. Result ID: 6a1ed933fbc373592c1ae65a.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6423dbd7150506f857d5.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 (ZS)"}. This record does not assert independent reproduction.

### MMS-1B

Amharic Performance: 100.7. Result ID: 6a1ed933fbc373592c1ae659.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6423dbd7150506f857d5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f681e209131cea455ec.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot (ZS)"}. This record does not assert independent reproduction.

### Omni.

Amharic Performance: 51.1. Result ID: 6a1ed933fbc373592c1ae658.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6423dbd7150506f857d5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6916b7900052cac1dc65e04a.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot (ZS)"}. This record does not assert independent reproduction.

### Whisp. T

Amharic Performance: 41.3. Result ID: 6a1ed933fbc373592c1ae65d.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6423dbd7150506f857d5.md>)

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

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

Recorded evaluation configuration: {"Evaluation Protocol":"Fine-tuned (FT)"}. This record does not assert independent reproduction.

### MMS-300M

Amharic Performance: 37.8. Result ID: 6a1ed933fbc373592c1ae65b.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6423dbd7150506f857d5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1e6423dbd7150506f857d5.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Fine-tuned (FT)"}. This record does not assert independent reproduction.

### Whisp. S

Amharic Performance: 33.6. Result ID: 6a1ed933fbc373592c1ae65c.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6423dbd7150506f857d5.md>)

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

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

Recorded evaluation configuration: {"Evaluation Protocol":"Fine-tuned (FT)"}. This record does not assert independent reproduction.

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