| --- |
| license: cc-by-nc-4.0 |
| base_model: Qwen/Qwen3-TTS-12Hz-1.7B-Base |
| datasets: |
| - Hebrish/Hebrish-TTS-Voice-Recordings |
| language: |
| - en |
| - he |
| pipeline_tag: text-to-speech |
| tags: |
| - tts |
| - qwen3-tts |
| - voice-clone |
| - code-switching |
| - hebrish |
| extra_gated_prompt: "Access to this model is by request and is governed by the Hebrish terms of use (https://hebrish.app/terms). Non-commercial use is free; commercial use needs a commercial licence from access@hebrish.app." |
| extra_gated_fields: |
| Name: text |
| Organisation: text |
| Intended use: text |
| "I agree to use this model under the Hebrish terms of use (non-commercial unless I hold a commercial licence)": checkbox |
| --- |
| |
| # Meorav v2.1 |
|
|
| A single-speaker text-to-speech fine-tune of [Qwen3-TTS-12Hz-1.7B-Base](https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-Base) |
| on one voice: Daniel Rosehill, Irish-accented English with Hebrew words mixed in ("Hebrish"). Meorav is |
| Hebrew for "mixed", as code-switching is. Part of [Hebrish Release v2](https://hebrish.app/releases#v2) |
| (2026-10-22), alongside Sabich v2.0 and Shakshuka v2.0. |
|
|
| **v2.1** is v2.0's recipe trained on cleaner audio: every take went through DeepFilterNet 3 (attenuation capped at |
| 15 dB) before the podcast processing chain. On the same 7 test sentences its background noise below 1 kHz is about |
| 5 dB lower than v2.0's, with the same voice bandwidth. Chosen over v2.0 by listening (Daniel, 2026-10-22). |
|
|
| **Access and terms of use.** Governed by the [Hebrish terms of use](https://hebrish.app/terms); access is by |
| request (button on this page, or [access@hebrish.app](mailto:access@hebrish.app)). Non-commercial |
| use is free; commercial use needs a commercial licence. |
|
|
| It has not been evaluated: no listening test or metric is reported here. |
|
|
| <!-- hebrish-listen:begin --> |
| ## Listen: what Hebrish is and how it's made |
|
|
| A spoken introduction to the project by the person who makes it: why Hebrish exists, why stock |
| speech-to-text gets Hebrew words wrong, how the fine-tunes are trained, the model lines (Sabich, |
| Jachnun, Shakshuka, Meorav), how the training data is recorded, and the plans for the apps. |
|
|
| | | | |
| | --- | --- | |
| | Listen | [hebrish.app/updates](https://hebrish.app/updates): player, chapters, edited transcript, MP3 download | |
| | Author | Daniel Rosehill | |
| | Recorded | 2026-10-22 | |
| | Runtime | 1:07:03 | |
|
|
| Chapters (each opens the player at that point): |
| [0:00](https://hebrish.app/updates#t=0) Why this voice note 路 |
| [1:36](https://hebrish.app/updates#t=96) Coming to speech to text 路 |
| [6:36](https://hebrish.app/updates#t=396) Why Hebrew words go wrong 路 |
| [9:23](https://hebrish.app/updates#t=563) How the fine-tune works 路 |
| [12:27](https://hebrish.app/updates#t=747) Why Parakeet, and the model plan 路 |
| [17:44](https://hebrish.app/updates#t=1064) Disfluencies, shekels, paragraphs 路 |
| [25:40](https://hebrish.app/updates#t=1540) Tech vocabulary and Meorav 路 |
| [29:07](https://hebrish.app/updates#t=1747) The kitchen sink: Sabich and Jachnun 路 |
| [33:35](https://hebrish.app/updates#t=2015) Licensing, accents, noisy recordings 路 |
| [39:10](https://hebrish.app/updates#t=2350) One recorder for ASR and TTS 路 |
| [41:04](https://hebrish.app/updates#t=2464) Desktop shortcuts and the macro pad 路 |
| [43:34](https://hebrish.app/updates#t=2614) Android: Bluetooth and one button 路 |
| [45:35](https://hebrish.app/updates#t=2735) Streaming and Shakshuka 路 |
| [50:28](https://hebrish.app/updates#t=3028) Long-form transcription 路 |
| [56:00](https://hebrish.app/updates#t=3360) Output modes 路 |
| [63:01](https://hebrish.app/updates#t=3781) Report a word, and more voices |
| <!-- hebrish-listen:end --> |
|
|
| ## Training |
|
|
| | | | |
| |---|---| |
| | Data | [`Hebrish/Hebrish-TTS-Voice-Recordings`](https://huggingface.co/datasets/Hebrish/Hebrish-TTS-Voice-Recordings), train split: 1,103 read takes, 88.2 min after trimming, 24 kHz; DeepFilterNet 3 (deepfilternet 0.5.6, `atten_lim_db` 15), then a podcast voice chain (EQ, de-ess, 2:1 compression, -20 LUFS) | |
| | Method | Full SFT, upstream `finetuning/sft_12hz.py` with fixes (label shift, sub-talker, `text_projection` applied in training), fp32 master weights with bf16 autocast | |
| | Schedule | LR 7e-6, 3 epochs, batch 2 x grad. accumulation 4, final checkpoint | |
| | Hardware | 1 x L40S (Modal) | |
|
|
| Numbers are spelled out in the training text, so write them out in prompts too ("four hundred and twelve"). |
|
|
| ## Version history |
|
|
| | Version | Date | Data | Repo | |
| |---|---|---|---| |
| | Meorav v2.1 | 2026-10-22 | 1,103 takes, 88.2 min, DeepFilterNet-cleaned | this repo | |
| | Meorav v2.0 | 2026-10-22 | 1,103 takes, 87.8 min | this repo, revision [`600a2820`](https://huggingface.co/Hebrish/Meorav/tree/600a282006eca86852f95ec68fec1524315fe092) | |
| | Meorav PoC-1 | 2026-10-22 | 657 takes, 50 min | [`Hebrish/TTS-V1`](https://huggingface.co/Hebrish/TTS-V1) | |
|
|
| ## Usage |
|
|
| ```python |
| import torch, soundfile as sf |
| from qwen_tts import Qwen3TTSModel |
| |
| tts = Qwen3TTSModel.from_pretrained("Hebrish/Meorav", device_map="cuda:0", dtype=torch.bfloat16) |
| wavs, sr = tts.generate_custom_voice(text="Yalla, I'll ring you after the match.", speaker="daniel", language="English") |
| sf.write("out.wav", wavs[0], sr) |
| ``` |
|
|
| Requires `qwen-tts` (tested with 0.1.1). The repo is gated: log in with a token that has access. |
|
|
| ## Licence |
|
|
| CC BY-NC 4.0, matching the dataset. The base model is Apache 2.0. |
|
|
| ## Base model and licence notices |
|
|
| This model is a fine-tune of [`Qwen/Qwen3-TTS-12Hz-1.7B-Base`](https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-Base), Copyright 2026 Alibaba Cloud, licensed under [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) (text in `LICENSE-Qwen-Apache-2.0`). Hebrish modified the base model by fine-tuning it. |
|
|
| The licence stated at the top of this card covers Hebrish's contribution; the base model's licence keeps applying to the base model, and nothing here restricts what that licence allows for it. Terms of use: <https://hebrish.app/terms>. |
|
|
| Hebrish is not affiliated with or endorsed by Alibaba Cloud. |
|
|
