You need to agree to share your Hugging Face information to access this model
This repository is publicly accessible, but you have to accept the conditions to access its files and content.
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.
Log in or Sign Up to review the conditions and access this model content.
Meorav v2.1
A single-speaker text-to-speech fine-tune of 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 (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; access is by request (button on this page, or 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.
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: 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 Why this voice note · 1:36 Coming to speech to text · 6:36 Why Hebrew words go wrong · 9:23 How the fine-tune works · 12:27 Why Parakeet, and the model plan · 17:44 Disfluencies, shekels, paragraphs · 25:40 Tech vocabulary and Meorav · 29:07 The kitchen sink: Sabich and Jachnun · 33:35 Licensing, accents, noisy recordings · 39:10 One recorder for ASR and TTS · 41:04 Desktop shortcuts and the macro pad · 43:34 Android: Bluetooth and one button · 45:35 Streaming and Shakshuka · 50:28 Long-form transcription · 56:00 Output modes · 63:01 Report a word, and more voices
Training
| Data | 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 |
| Meorav PoC-1 | 2026-10-22 | 657 takes, 50 min | Hebrish/TTS-V1 |
Usage
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.
- Downloads last month
- -