Meorav-Multi-Voice / README.md
danielrosehill's picture
Card: voice names (Josh, Rivka, Nigel, Fiona, Bazza) and avatars, proof-of-concept badge
210e728 verified
|
Raw History Blame Contribute Delete
6.46 kB
---
license: cc-by-nc-4.0
base_model: Qwen/Qwen3-TTS-12Hz-1.7B-Base
base_model_relation: finetune
language:
- en
- he
pipeline_tag: text-to-speech
tags:
- tts
- qwen3-tts
- voice-clone
- meorav
- code-switching
- hebrish
- multi-speaker
extra_gated_prompt: 'Access is approved automatically once you accept the terms. Use
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
I agree to receive Hebrish model updates by email (at most once a month; unsubscribe any time): checkbox
---
# Meorav-Multi-Voice
![Status: proof of concept](https://img.shields.io/badge/status-proof%20of%20concept-9a3412)
> **Proof of concept.** v1.0 was not trained on enough data, so the Hebrew code-switching did not transfer as well
> as hoped: gutturals such as the "ch" in *chag* and *achi* are not always produced. Listen before you rely on it:
> [Meorav-Samples](https://huggingface.co/spaces/Hebrish/Meorav-Samples#multi-voice). More: <https://hebrish.app/models/meorav-multi-voice>.
English text-to-speech with Hebrew words mixed in ("Hebrish"), in **five designed voices** from one model.
It is a full fine-tune of [Qwen3-TTS-12Hz-1.7B-Base](https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-Base),
continued from [Meorav-Daniel](https://huggingface.co/Hebrish/Meorav-Daniel). The voice is picked by a short
reference clip (x-vector conditioning); the clips for the five voices are in `voices/`.
None of the five voices is a real person: each was designed from a text description with OmniVoice
(`"<gender>, young adult, moderate pitch, <accent> accent"`), then fixed to one seed.
| Avatar | Name | Voice | Reference clip |
|---|---|---|---|
| <img src="https://huggingface.co/spaces/Hebrish/Meorav-Samples/resolve/main/voices/josh-512.png" alt="Josh" width="64"> | **Josh** | American male (A3) | `voices/american-male.wav` |
| <img src="https://huggingface.co/spaces/Hebrish/Meorav-Samples/resolve/main/voices/rivka-512.png" alt="Rivka" width="64"> | **Rivka** | American female | `voices/american-female.wav` |
| <img src="https://huggingface.co/spaces/Hebrish/Meorav-Samples/resolve/main/voices/nigel-512.png" alt="Nigel" width="64"> | **Nigel** | British male | `voices/british-male.wav` |
| <img src="https://huggingface.co/spaces/Hebrish/Meorav-Samples/resolve/main/voices/fiona-512.png" alt="Fiona" width="64"> | **Fiona** | British female | `voices/british-female.wav` |
| <img src="https://huggingface.co/spaces/Hebrish/Meorav-Samples/resolve/main/voices/bazza-512.png" alt="Bazza" width="64"> | **Bazza** | Australian male | `voices/australian-male.wav` |
Pass the reference clip for the voice you want (`ref_audio`, see Usage). The names and avatars are illustrations,
not real people; copies of the avatars are in `figures/voices/` (the card shows them from the public
[Meorav-Samples](https://huggingface.co/spaces/Hebrish/Meorav-Samples) Space, since files in this gated repo need access).
**Access and terms of use.** Governed by the [Hebrish terms of use](https://hebrish.app/terms); access is
approved automatically once you accept them (button on this page, or [access@hebrish.app](mailto:access@hebrish.app)).
Non-commercial use is free; commercial use needs a commercial licence.
## Related models
| Model | Voice |
|---|---|
| [Meorav-Daniel](https://huggingface.co/Hebrish/Meorav-Daniel) | Daniel Rosehill's own voice (Irish-accented English) |
| [Meorav](https://huggingface.co/Hebrish/Meorav) | One designed American male voice (OmniVoice LoRA, v3.0) |
| **Meorav-Multi-Voice** (this repo) | Five designed voices, one model |
## Training (run `mv1`, 2026-11-16)
- **Init:** Meorav-Daniel weights with the base model's speaker encoder restored, so new voices can be conditioned by x-vector.
- **Data:** 2,147 rows. 461 of Daniel Rosehill's code-switching takes, counted twice (922 rows), trained **only on
their Hebrew-word spans** (the English parts are masked out of the loss), so the voices learn how the Hebrew words are
said without taking on his voice. Plus 245 English lines per designed voice (about 27–31 min each), generated with OmniVoice, trained in full.
Every row is conditioned on its own speaker's x-vector.
- **Recipe:** 3 epochs, lr 1e-5, batch 4 × grad accum 4 (effective 16), one A100-80GB on Modal. This is the epoch-3 checkpoint.
- Training code: Qwen3-TTS fine-tuning at commit `022e286b`, with a span-masked SFT script.
## Usage
```python
import torch, soundfile as sf
from huggingface_hub import hf_hub_download
from qwen_tts import Qwen3TTSModel
repo = "Hebrish/Meorav-Multi-Voice"
tts = Qwen3TTSModel.from_pretrained(repo, device_map="cuda:0", dtype=torch.bfloat16)
ref = hf_hub_download(repo, "voices/british-female.wav") # Fiona
wavs, sr = tts.generate_voice_clone(text="Yalla, let's go, we're already late for the brit mila.",
language="English", ref_audio=ref, x_vector_only_mode=True)
sf.write("out.wav", wavs[0], sr)
```
Requires `qwen-tts`. The repo is gated: log in with a token that has access. Write Hebrew words in Latin letters,
the way an English speaker in Israel would spell them.
## Limitations
- Not benchmarked: no listening score or metric is reported. The renders were checked by ear only.
- Gutturals (ח, the "ch" in *chag*, *achi*) are not always produced.
- Training clips were at most 15 s; generate long text sentence by sentence.
- Other voices can be tried with any reference clip, but only the five above were trained.
## Licence
CC BY-NC 4.0. 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.