You can deploy this model and start earning money today!

Maax-Bits/
oron-tts-bucket

Name: oron-tts-bucket
Availability: InStock

Views

No views yet

OronTTS — F5-TTS for Mongolian & Kazakh

Non-autoregressive text-to-speech model based on F5-TTS (Flow Matching + Diffusion Transformer) for Mongolian (Khalkha Cyrillic) and Kazakh (Cyrillic).

Model Details

Parameter	Value
Architecture	F5-TTS (OT-CFM + DiT + Vocos)
dim	512
depth	12
heads	8
vocab_size	65
sample_rate	24000 Hz
mel_bins	100

Usage

python

from src.models.f5tts import F5TTS
from src.utils.checkpoint import CheckpointManager

model = F5TTS.from_config(config)
cm = CheckpointManager("checkpoints")
cm.load(model, path="f5tts_best.pt", device="cuda")

wav = model.synthesize(
    text="Сайн байна уу",
    lang="mn",
    ref_audio_path="ref.wav",
)

Training

Trained on btsee/mbspeech_mn (3,846 Mongolian speech samples).

License

MIT

Maax-Bits/oron-tts-bucket