GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
texdata
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
texdata
Model Tree
maya-research/maya1
Input Modalities
Output Modalities
Supported Functionality
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:
bash
pip install transformers peft torch snac soundfile phonemizer # + an espeak-ng shared libhuggingface-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.wavpython maya_tts.py -t "To je čudovito!" -a texdata/Maya1-Slovenian-TTS -e veselo -o out.wavpython maya_tts.py --list-emotions
bash
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)
python
import os, torch, soundfile as sfos.environ.setdefault("PHONEMIZER_ESPEAK_LIBRARY", "/usr/lib/x86_64-linux-gnu/libespeak-ng.so.1")from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelfrom snac import SNACfrom phonemizer.backend import EspeakBackendfrom phonemizer.separator import SeparatorCODE_START, CODE_END, OFFSET = 128257, 128258, 128266SNAC_MIN, SNAC_MAX = 128266, 156937dev = "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 spotphonemes = be.phonemize([text], separator=Separator(phone="", word=" "), strip=True)[0] # REQUIREDcontent = 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 audiosf.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):
bibtex
@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:
bibtex
@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.