Loading…
Loading…
Trained by MediaAtlas — LLM fine-tuning on your own data, trained in the EU, weights delivered. Pricing · All our models
A LoRA adapter that adapts maya-research/maya1 (a 3B Orpheus-style speech LM that autoregressively generates SNAC-24kHz codec tokens) to Slovenian.
The key design choice is a phoneme front-end: Maya1 is grapheme-based and English-pretrained, so
it applies English grapheme-to-phoneme rules to Slovenian text (mispronunciations, wrong or missing
stress — Slovenian orthography does not mark stress, word-boundary errors). This adapter is trained on
espeak-ng sl IPA phonemes instead of raw text, so the model only has to learn phoneme-to-acoustic.
This gives markedly more accurate Slovenian pronunciation.
You MUST phonemize input text with espeak-ng sl before inference — the model expects IPA, not
graphemes. Feeding raw Slovenian text will not work correctly.
Synthesize held-out ARTUR validation texts, transcribe back with a Slovenian ASR model, compare (jiwer):
| model | WER | CER |
|---|---|---|
| grapheme, clean multi-speaker | 21.8% | 5.0% |
| phoneme (this model) | 24.8% | 4.2% |
CER (character error rate) is the cleaner phonetic-accuracy metric and is the lowest of every variant we trained — the phoneme front-end measurably improves pronunciation. (WER is more sensitive to the ASR model and word boundaries; the difference is within noise at n=15.)
LlamaForCausalLM, generates SNAC-24kHz tokens, Apache-2.0).A Slovenian voice, speaker {id}.).128266 + pos*4096 + code layout).sl via the phonemizer library, with_stress=True.q,k,v,o,gate,up,down, 2 epochs, LR 1e-4, bf16,
gradient checkpointing. Target = [CODE_START] + snac_ids + [CODE_END], loss only on the audio side.A self-contained CLI maya_tts.py is included in this repo — it handles phonemization,
generation and decoding for you:
pip install transformers peft torch snac soundfile phonemizer # + an espeak-ng shared lib
huggingface-cli download texdata/Maya1-Slovenian-TTS maya_tts.py --local-dir .
python maya_tts.py -t "Danes je lep sončen dan." -a texdata/Maya1-Slovenian-TTS -o out.wav
python maya_tts.py -t "To je čudovito!" -a texdata/Maya1-Slovenian-TTS -e veselo -o out.wav
python maya_tts.py --list-emotions
pip install transformers peft torch snac soundfile phonemizer
# espeak-ng shared lib must be present (Debian/Ubuntu: apt-get install espeak-ng-data,
# or set PHONEMIZER_ESPEAK_LIBRARY to your libespeak-ng.so)
import os, torch, soundfile as sf
os.environ.setdefault("PHONEMIZER_ESPEAK_LIBRARY", "/usr/lib/x86_64-linux-gnu/libespeak-ng.so.1")
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
from snac import SNAC
from phonemizer.backend import EspeakBackend
from phonemizer.separator import Separator
CODE_START, CODE_END, OFFSET = 128257, 128258, 128266
SNAC_MIN, SNAC_MAX = 128266, 156937
dev = "cuda"
tok = AutoTokenizer.from_pretrained("maya-research/maya1")
model = AutoModelForCausalLM.from_pretrained("maya-research/maya1", dtype=torch.bfloat16).to(dev)
model = PeftModel.from_pretrained(model, "texdata/Maya1-Slovenian-TTS").eval()
snac = SNAC.from_pretrained("hubertsiuzdak/snac_24khz").eval().to(dev)
be = EspeakBackend("sl", with_stress=True, preserve_punctuation=True)
def unpack_snac(ids):
frames = len(ids) // 7; ids = ids[:frames*7]; l1,l2,l3 = [],[],[]
for i in range(frames):
s = ids[i*7:(i+1)*7]
l1.append((s[0]-OFFSET)%4096)
l2 += [(s[1]-OFFSET)%4096, (s[4]-OFFSET)%4096]
l3 += [(s[2]-OFFSET)%4096, (s[3]-OFFSET)%4096, (s[5]-OFFSET)%4096, (s[6]-OFFSET)%4096]
return [l1,l2,l3]
def synth(text, desc="A Slovenian voice, speaker Artur-B-G0911.", temperature=0.75): # 0.75 = natural sweet spot
phonemes = be.phonemize([text], separator=Separator(phone="", word=" "), strip=True)[0] # REQUIRED
content = f'<description="{desc}"> {phonemes}'
prompt = tok.apply_chat_template([{"role": "user", "content": content}],
tokenize=False, add_generation_prompt=True)
ids = tok(prompt, add_special_tokens=False, return_tensors="pt").input_ids.to(dev)
out = model.generate(ids, max_new_tokens=1800, do_sample=True, temperature=temperature,
top_p=0.9, repetition_penalty=1.1, eos_token_id=CODE_END, pad_token_id=CODE_END)
gen = out[0, ids.shape[1]:].tolist()
snac_ids = [t for t in gen if SNAC_MIN <= t <= SNAC_MAX]
codes = [torch.tensor(c, device=dev).unsqueeze(0) for c in unpack_snac(snac_ids)]
audio = snac.decoder(snac.quantizer.from_codes(codes))[0,0].detach().cpu().numpy()
return audio
sf.write("out.wav", synth("Danes je lep sončen dan in ptice pojejo."), 24000)
<laugh>, <sigh>, ...) and emotional voice
descriptions in English. This adapter was fine-tuned on neutral read ARTUR speech, so Slovenian
emotional control is limited; expect neutral prosody. Cross-lingual emotional fine-tuning is future work.repetition_penalty=1.1 is important — it prevents non-termination (runaway generation with no
CODE_END) on short inputs.max_new_tokens must cover your longest utterance (~1800 for ~10s) or the audio truncates.Apache-2.0, inherited from the base model maya-research/maya1.
Cite this work (Tadej Fius, MediaAtlas Ltd):
@misc{fius2026maya,
title = {Maya1 Slovenian TTS},
author = {Fius, Tadej},
year = {2026},
publisher = {MediaAtlas Ltd},
howpublished = {Hugging Face},
url = {https://huggingface.co/texdata/Maya1-Slovenian-TTS}
}
Upstream / source citations:
@misc{maya1, title={Maya1 (Orpheus-style speech LM)}, author={{Maya Research}}, note={Apache-2.0}, url={https://huggingface.co/maya-research/maya1}}
@misc{siuzdak2024snac, title={SNAC: Multi-Scale Neural Audio Codec}, author={Siuzdak, Hubert}, year={2024}, url={https://github.com/hubertsiuzdak/snac}}
LoRA adapter over maya-research/maya1 (SNAC-24kHz). Cite the base + SNAC codec.
maya-research/maya1