# Text-to-Speech on DIRNDL 100 German radio news texts (test)

Source: [Text-to-Speech on DIRNDL 100 German radio news texts (test)](<https://www.sota2.com/research/sota/text-to-speech-on-dirndl-100-german-radio-news-texts-test>)

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

Data updated: 2026-02-26T06:08:25.379Z

Evaluation of Text-to-Speech synthesis quality using the test split of the DIRNDL 100 German radio news texts dataset, typically 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 | Text-to-Speech |
| Dataset (including any stated split) | DIRNDL 100 German radio news texts (test) |
| Metric | WER |
| 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

- [WER](<https://www.sota2.com/research/sota/text-to-speech-on-dirndl-100-german-radio-news-texts-test.md?metric=WER>): Lower is better; unit: SCALAR.

## Recorded results

| Method | WER | Result date | Report paper |
| --- | --- | --- | --- |
| FastSpeech 2 | 0.097 | Not recorded | 68fa6bf01e209131cea31006 |
| FastSpeech 2 | 0.099 | Not recorded | 68fa6bf01e209131cea31006 |
| Tacotron 2 | 0.127 | Not recorded | 68fa6bf01e209131cea31006 |
| Tacotron 2 | 0.131 | Not recorded | 68fa6bf01e209131cea31006 |

### FastSpeech 2

WER: 0.097. Result ID: 698ea94bffc3901de09f909a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf01e209131cea31006.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bf01e209131cea31006.md>)

[Implementation](<https://github.com/DigitalPhonetics/IMS-Toucan>)

Recorded evaluation configuration: {"Training Regime":"Low-Resource"}. This record does not assert independent reproduction.

### FastSpeech 2

WER: 0.099. Result ID: 698ea94bffc3901de09f9099.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf01e209131cea31006.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bf01e209131cea31006.md>)

[Implementation](<https://github.com/DigitalPhonetics/IMS-Toucan>)

Recorded evaluation configuration: {"Training Regime":"Baseline"}. This record does not assert independent reproduction.

### Tacotron 2

WER: 0.127. Result ID: 698ea94bffc3901de09f9098.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf01e209131cea31006.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bf01e209131cea31006.md>)

[Implementation](<https://github.com/DigitalPhonetics/IMS-Toucan>)

Recorded evaluation configuration: {"Training Regime":"Low-Resource"}. This record does not assert independent reproduction.

### Tacotron 2

WER: 0.131. Result ID: 698ea94bffc3901de09f9097.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bf01e209131cea31006.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bf01e209131cea31006.md>)

[Implementation](<https://github.com/DigitalPhonetics/IMS-Toucan>)

Recorded evaluation configuration: {"Training Regime":"Baseline"}. This record does not assert independent reproduction.

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