whatmodel.sh / tts / Piper (tr_TR dfki medium)
Piper (tr_TR dfki medium)
↗ share
+ contribute
Piper (tr_TR dfki medium) is an open-weights text-to-speech model from Open Home Foundation (Piper), released June 2023. Licence: mit.
Catalogue identity notes
Piper voice tr_TR-dfki-medium from rhasspy/piper-voices (tr/tr_TR/dfki/medium/tr_TR-dfki-medium.onnx, 63,201,294 bytes at c10ece1), run with piper-tts. The Antalia re-run loads piper/tr_TR-dfki-medium.onnx on CPU (harness/systems/run_piper.py). Other Piper voices (e.g. the catalogued en_US lessac medium) are separate checkpoints.
Model information sources
Score within the Vapi Humanness · Bradley–Terry rating, 2026-09-25 snapshot comparison set only.
$ how it compares
The text-to-speech models ranked either side of Piper (tr_TR dfki medium), out of 148 with a score, then more from Open Home Foundation (Piper).
| # | model | score | where | ||
|---|---|---|---|---|---|
| 135 |  Glow-TTS + HiFi-GAN (VCTK, VITS study) | 28±6 | comparison only | ||
| 136 |  HierSpeech++ (LibriTTS-960) | 28±5 | local | ||
| 137 | Piper (tr_TR dfki medium) | 26±4 | local | ||
| 138 |  OpenVoice V2 | 26±3 | local | ||
| 139 |  Bark | 25±3 | local | ||
| more from Open Home Foundation (Piper) | |||||
| 96 | Piper (en_US lessac medium) | 47±5 | local | ||
see all text-to-speech models · find the ones that fit your machine
$ what it's good at
other tests1 not in a task · 94% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Freya-TR-Eval Turkish TTS intelligibility (WER, faster-whisper large-v3, 8 kHz band) | 3.4% ✎ | ▄··▄··▄···▂█ beats 5/10 | 94% |
$ where to run it
Other ways to run it
- Run it as published · needs ~0.06 GB · from github.com/OHF-Voice (official)
pip install piper-tts && python3 -m piper.download_voices tr_TR-dfki-medium && python3 -m piper -m tr_TR-dfki-medium -f test.wav -- 'Merhaba, nasılsınız?'
Weights and documentation: huggingface.co/rhasspy ↗
$ how the score was worked out · Antalia-2 Mini model card (cl… 94%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 Antalia-2 Mini model card (cloud0day3/antalia-mini), public Freya-TR-Eval re-run table | 1 | 94% |
| prior · pull toward the middle | 6% | |
| weighted average | = 26.3 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json