servinosmanov/xtts-crh-sevil-v1

XTTS Crimean Tatar - Sevil Voice (v1)

Text-to-Speech model for Crimean Tatar (Qırımtatar tili) language based on XTTS v2 architecture.

Model Description

• Language: Crimean Tatar (crh)
• Voice: Sevil (female)
• Architecture: XTTS v2 (Coqui TTS)
• Training: Fine-tuned on ~7 hours of Crimean Tatar speech data
• Base Model: XTTS v2 Multilingual

Usage

Installation

pip install TTS

Python API

from TTS.tts.configs.xtts_config import XttsConfig
from TTS.tts.models.xtts import Xtts
import torch

# Load model
config = XttsConfig()
config.load_json("config.json")

model = Xtts.init_from_config(config)
model.load_checkpoint(
    config,
    checkpoint_path="model.pth",
    vocab_path="vocab.json",
    use_deepspeed=False,
)
model.cuda()
model.eval()

# Generate speech
# Text should be in Cyrillic script
text = "Селям алейкум! Бу къырымтатар тилинде сёйлеген модель."

gpt_cond_latent, speaker_embedding = model.get_conditioning_latents(
    audio_path="reference.wav"
)

out = model.inference(
    text=text,
    language="ru",  # Use "ru" for Cyrillic text
    gpt_cond_latent=gpt_cond_latent,
    speaker_embedding=speaker_embedding,
)

# Save audio
import torchaudio
wav = torch.tensor(out["wav"]).unsqueeze(0)
torchaudio.save("output.wav", wav, 24000)

Text Format

The model expects text in Cyrillic script. If your text is in Latin script, convert it first:

Latin	Cyrillic
a	а
ğ	гъ
q	къ
ñ	нъ
j	ж
ş	ш
ç	ч

Training Details

• Dataset: Sevil voice recordings (~7 hours)
• Epochs: Averaged weights from epochs 4 and 7 (50/50)
• Batch Size: 2
• Learning Rate: 5e-6
• Optimizer: AdamW

Limitations

• Best results with sentences under 200 characters
• Some phonemes specific to Crimean Tatar may vary in quality
• Works best with reference audio from the same speaker

Our another resources

• Crimeantatar TTS model based on SpeechT5 Sevil model on SpeechT5
• Fixed Sevil dataset

Citation

@misc{xtts-crh-sevil-v1,
  author = {Servin Osmanov},
  title = {XTTS Crimean Tatar - Sevil Voice},
  year = {2026},
  publisher = {Hugging Face},
  url = {https://huggingface.co/servinosmanov/xtts-crh-sevil-v1}
}

License

Apache 2.0