Meorav-Daniel
Text-to-speech in Daniel's own voice: Irish-accented English with the Hebrew words said his way
Text-to-speech in one real voice, Daniel Rosehill's: Irish-accented English with the Hebrew words said the Anglo-Israeli way. A full fine-tune of Qwen3-TTS on his own recordings, cleaned with RE-USE, no voice conversion. v1.0 is the model first published as Meorav v2.2; not benchmarked.
Status
On 2026-11-15 the Meorav line split in two. Meorav moved to a designed synthetic voice, aiming at a neutral accent, while Daniel's own voice continues here. Meorav-Daniel v1.0 is the Meorav v2.2 model (2026-11-09) with byte-identical weights, copied to Hebrish/Meorav-Daniel. It was trained on 3,995 screened code-switching takes, about 5.5 hours, each cleaned with NVIDIA NemotronLabs RE-USE. It has no benchmark and no listening score. The samples on Hebrish/Meorav-Samples under release/ are this model (then Meorav v2.2). Meorav-Daniel is also the starting point for Meorav-Multi-Voice (2026-11-16), which keeps its Hebrew-word pronunciation in five designed voices.
| Base model | Qwen/Qwen3-TTS-12Hz-1.7B-Base (Qwen) |
| Current version | Meorav-Daniel v1.0, released 2026-11-15 |
| Parameters | 1.92B (1,916,676,352 in model.safetensors, bf16, safetensors header count) plus the 170,557,441-parameter speech tokenizer |
| Evaluation | No benchmark and no listening score Status on this page · Training pipeline and run log |
| Access | Gated, automatic: accept the terms on Hugging Face and access is approved instantly. Accept terms and download on Hugging Face |
| Download | every format and quant (Hugging Face) |
| Collection | Hebrish/hebrish-english-hebrew-code-switching on Hugging Face |
| Licence | CC-BY-NC-4.0 · use governed by the terms of use |
| Used by | Your own tools (qwen-tts); the Meorav app (beta) runs these weights (as Meorav v2.2); the Hebrish apps do not offer text-to-speech |
| DOIs | none yet |
Samples
Ten texts of various lengths, one take each: the untuned Qwen3-TTS base cloning Daniel's voice zero-shot (before) against Meorav-Daniel v1.0 (after). These are the release samples from when the weights were published as Meorav v2.2. Unvalidated.
Yalla, let's go, we're already late for the brit mila.
We're doing a quiet shabbat this week, just challah, some chamin and an early night.
I spent the whole morning at Misrad Hapnim, and I still don't have the teudat zehut.
Everyone here says everything will happen acharei hachagim. I used to find it frustrating, but honestly, after a few years you start saying it yourself.
On Friday morning I went down to the shuk for the usual run. The guy at the bourekas stall remembered me, gave me an extra one, and told me to say shabbat shalom to the kids.
The arnona bill came in twice this month, so I rang the iriya. After forty minutes on hold they told me, beseder, it's a mistake, just ignore the second one.
When I started ulpan, the morah told us not to worry about the grammar yet. Just listen, she said, and the words will come. She was right about most of it, although I still mix up my verb patterns when I'm tired. These days I can argue with the makolet guy about the price of cottage cheese, which feels like real progress.
Our shul does a kiddush after davening every shabbat, and it has become the real centre of the week. You hear about every simcha, every new oleh, and who is looking for a chavruta. The gabbai keeps a list of who is bringing what, and somehow there is always too much kugel. If you are new to the neighbourhood, honestly, just turn up, nobody will let you stand on your own for long.
Last chol hamoed we did a tiyul up in the Galil with the whole mishpacha. We stopped for shakshuka at a little place near the Kinneret, then walked along the Jordan for an hour. My father-in-law kept telling everyone it was nothing compared to the old days, before the road was paved. By the time we got back to Yerushalayim it was nearly midnight, and the kids were fast asleep in the back.
When we made aliyah, the first few months were a blur of paperwork. There was the misrad haklita, the kupat cholim, Bituach Leumi, and a bank that wanted three copies of everything. Our neighbour, a sabra who had seen it all before, sat us down with a cup of coffee and said, savlanut, it all gets done eventually. She was right. By our first Pesach in the country we had a lease, a car, and a teudat oleh that was already falling apart from use. Looking back now, the bureaucracy is not what I remember. What I remember is the people who helped, without being asked, and the way the whole street seemed to come out for Yom Haatzmaut.
All demo audio is also in the public dataset Hebrish/Demos on Hugging Face.
Formats
| Repository | Format and files | Version | For | DOI |
|---|---|---|---|---|
Hebrish/Meorav-Daniel main | Qwen3-TTS full fine-tune (safetensors) model.safetensors 3.8 GB, speech tokenizer 0.7 GB, tokenizer and config; tag v1.0 · accept terms · files | v1.0 | qwen-tts (Qwen3TTSModel) | none yet |
Hugging Face issues a DOI per repository, so each format can be cited on its own. Repositories, sizes and DOIs checked on the Hub on 2026-11-15.
Versions
| Version | Released | Run | Where | Notes |
|---|---|---|---|---|
| Meorav-Daniel v1.0 current | 2026-11-15 | meorav-v22-reuse | Meorav-Daniel @ v1.0 | The Meorav v2.2 weights (2026-11-09), copied unchanged when Meorav moved to a designed voice: 3,995 screened code-switching takes (about 5.5 h) enhanced with NVIDIA NemotronLabs RE-USE; same training settings as Meorav v2.1; not evaluated |
Access
Accept the terms on Hugging Face. The main Meorav-Daniel repository is gated automatically: open it, sign in, accept the terms, and access is approved instantly.
Cite
Meorav-Daniel has no DOI yet; cite the repository, Hebrish/Meorav-Daniel.
@misc{rosehill_meorav_daniel_2026,
author = {Daniel Rosehill},
title = {Meorav-Daniel},
year = {2026},
publisher = {Hugging Face},
url = {https://huggingface.co/Hebrish/Meorav-Daniel}
}