# Language Modeling on Hindi conversational Whisper-v3 transcriptions (test)

Source: [Language Modeling on Hindi conversational Whisper-v3 transcriptions (test)](<https://www.sota2.com/research/sota/language-modeling-on-hindi-conversational-whisper-v3-transcriptions-test>)

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

Data updated: 2026-04-28T07:50:28.867Z

Evaluation of Language Modeling performance using Perplexity (PPL) on the test split of the Hindi conversational Whisper-v3 transcriptions dataset.

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 | Language Modeling |
| Dataset (including any stated split) | Hindi conversational Whisper-v3 transcriptions (test) |
| Metric | Perplexity (PPL) |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 4 of 4 |
| 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

- [Perplexity (PPL)](<https://www.sota2.com/research/sota/language-modeling-on-hindi-conversational-whisper-v3-transcriptions-test.md?metric=Perplexity%20(PPL)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Perplexity (PPL) | Result date | Report paper |
| --- | --- | --- | --- |
| Ground-truth | 237.1 | Not recorded | 69f03eea55a3c32af89f9eed |
| Human-1 | 356.9 | Not recorded | 69f03eea55a3c32af89f9eed |
| Human-1 | 467.1 | Not recorded | 69f03eea55a3c32af89f9eed |
| Human-1 | 640.6 | Not recorded | 69f03eea55a3c32af89f9eed |

### Ground-truth

Perplexity (PPL): 237.1. Result ID: 69f0664b47f34ce924d60947.

[Reporting paper](<https://www.sota2.com/research/paper/69f03eea55a3c32af89f9eed.md>)

Recorded evaluation configuration: {"temperature (τ)":"–"}. This record does not assert independent reproduction.

### Human-1

Perplexity (PPL): 356.9. Result ID: 69f0664b47f34ce924d60948.

[Reporting paper](<https://www.sota2.com/research/paper/69f03eea55a3c32af89f9eed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f03eea55a3c32af89f9eed.md>)

Recorded evaluation configuration: {"temperature (τ)":"0.8"}. This record does not assert independent reproduction.

### Human-1

Perplexity (PPL): 467.1. Result ID: 69f0664b47f34ce924d60949.

[Reporting paper](<https://www.sota2.com/research/paper/69f03eea55a3c32af89f9eed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f03eea55a3c32af89f9eed.md>)

Recorded evaluation configuration: {"temperature (τ)":"0.9"}. This record does not assert independent reproduction.

### Human-1

Perplexity (PPL): 640.6. Result ID: 69f0664b47f34ce924d6094a.

[Reporting paper](<https://www.sota2.com/research/paper/69f03eea55a3c32af89f9eed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f03eea55a3c32af89f9eed.md>)

Recorded evaluation configuration: {"temperature (τ)":"1.0"}. This record does not assert independent reproduction.

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